© 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. 33210
    Prev
    Next
    INDEX
    Explanations

    scientific research terms and references

    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
    23
    +0.17
    0.6%
    651
    +0.16
    0.6%
    12
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.17
    0.06
    651
    +0.16
    0.04
    340
    +0.14
    0.04
    Negative Logits
    canon
    -0.92
    OUNT
    -0.84
    bucks
    -0.79
    @#&
    -0.78
    esses
    -0.75
    ipple
    -0.75
    IFT
    -0.75
    rontal
    -0.75
     Polaris
    -0.73
    Days
    -0.72
    POSITIVE LOGITS
     seq
    1.37
     al
    1.10
    sis
    1.07
     Associates
    1.07
    rics
    1.04
     nos
    1.00
    rees
    0.95
    ree
    0.90
     et
    0.89
    rog
    0.88
    Activations Density 1.818%

    No Known Activations