© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    5. GPT2-Small
    7. Residual Similar CE Local
    9. 6-RES_SCL-AJT
    11. 33283
    Prev
    Next
    INDEX
    Explanations

    differences or inconsistencies in text data, such as incorrect subtitles, disputed authorship, adjusted stats, and validation formats

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-ajt
    Prompts (Dashboard)
    12,288 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    46,080
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    apollo-research/Skylion007-openwebtext-tokenizer-gpt2
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.24
    1.3%
    459
    +0.10
    0.6%
    93
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    385
    +0.24
    0.22
    336
    +0.10
    0.07
    393
    +0.08
    0.38
    Negative Logits
    Rh
    -0.67
     Adin
    -0.66
     Chero
    -0.66
    Kn
    -0.62
     Hungry
    -0.62
     Smy
    -0.61
     Rhod
    -0.61
    lly
    -0.60
     Blind
    -0.59
    Ash
    -0.59
    POSITIVE LOGITS
     program
    0.79
     programme
    0.76
     procedure
    0.76
     system
    0.71
     scenario
    0.69
     category
    0.69
     ensemble
    0.69
     lineup
    0.67
     sequence
    0.67
     stat
    0.67
    Activations Density 27.149%

    No Known Activations