© 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. 34969
    Prev
    Next
    INDEX
    Explanations

    information related to technical details and links in documents

    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
    0.9%
    606
    +0.16
    0.6%
    442
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.24
    -0.03
    606
    +0.16
    0.12
    731
    +0.13
    0.04
    Negative Logits
     ACTIONS
    -0.93
    »Ĵ
    -0.87
     Direction
    -0.81
     Ruth
    -0.80
    ĺħ
    -0.80
     Loving
    -0.78
     Aging
    -0.78
    VERTISEMENT
    -0.77
     Forth
    -0.77
    Ļ½
    -0.77
    POSITIVE LOGITS
    agnar
    1.15
    imgur
    1.06
    ebin
    1.01
    online
    0.96
    proxy
    0.94
    bnb
    0.94
    yp
    0.92
    archives
    0.92
    bleacher
    0.92
    pir
    0.91
    Activations Density 10.314%

    No Known Activations