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

    Neuronpedia

    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. 33861
    Prev
    Next
    INDEX
    Explanations

    book titles and related terms

    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
    1.1%
    481
    +0.15
    0.7%
    506
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.24
    0.08
    406
    +0.15
    0.12
    26
    +0.10
    0.14
    Negative Logits
     unden
    -0.76
     encount
    -0.70
     carbohyd
    -0.67
     volunte
    -0.63
    isco
    -0.62
    ãģĦ
    -0.62
    vernment
    -0.59
     behavi
    -0.59
    ggie
    -0.59
    quit
    -0.58
    POSITIVE LOGITS
    holders
    0.89
     diameter
    0.84
    holder
    0.83
    cloth
    0.83
    builders
    0.82
    lines
    0.82
    stones
    0.81
    ridges
    0.81
    lain
    0.80
    pole
    0.79
    Activations Density 15.948%

    No Known Activations