© 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 EvalsExportsinterp-engineNEWAPI 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. 35571
    Prev
    Next
    INDEX
    Explanations

    statements phrased emphatically or bluntly

    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
    218
    +0.13
    0.5%
    131
    +0.11
    0.4%
    41
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.13
    0.11
    119
    +0.11
    0.11
    671
    +0.11
    0.08
    Negative Logits
    estic
    -0.95
    olin
    -0.80
    strom
    -0.79
    Pg
    -0.77
    ilver
    -0.77
    ãĥį
    -0.76
    ivery
    -0.76
    aceous
    -0.75
    atile
    -0.75
    ãĥĻ
    -0.74
    POSITIVE LOGITS
     hypot
    1.22
     analogy
    1.14
     nutshell
    1.07
     suffice
    0.97
     anecd
    0.97
     metaphor
    0.96
     guess
    0.96
     suppose
    0.96
    facts
    0.94
     perspective
    0.88
    Activations Density 14.735%

    No Known Activations