© 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. 33396
    Prev
    Next
    INDEX
    Explanations

    information related to practical skills and do-it-yourself tasks

    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
    393
    +0.18
    0.7%
    447
    +0.13
    0.5%
    699
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.17
    567
    +0.13
    0.08
    184
    +0.13
    0.04
    Negative Logits
    agonists
    -0.82
    ceptions
    -0.80
    iculture
    -0.79
    idered
    -0.73
    UME
    -0.73
    idia
    -0.72
    odder
    -0.70
    umed
    -0.70
    hari
    -0.70
     ........
    -0.70
    POSITIVE LOGITS
     much
    0.93
    soever
    0.85
     MUCH
    0.85
    beit
    0.85
    itzer
    0.84
    HCR
    0.84
    ever
    0.83
     exactly
    0.82
    ells
    0.81
    ls
    0.81
    Activations Density 6.228%

    No Known Activations