© 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
    2. Apollo Research · Taylor · Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
    3. GPT2-Small
    4. Residual Similar CE Local
    5. 6-RES_SCL-AJT
    6. 34963
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and personal names

    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
    99
    +0.13
    0.7%
    351
    +0.12
    0.7%
    169
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.29
    326
    +0.12
    0.26
    99
    +0.10
    0.15
    Negative Logits
    urers
    -0.77
    ional
    -0.76
    ored
    -0.75
    ī
    -0.72
    illus
    -0.70
    aneous
    -0.70
    achusetts
    -0.69
    rities
    -0.69
    ination
    -0.69
    rations
    -0.69
    POSITIVE LOGITS
    lly
    0.64
     Chrys
    0.60
     Akin
    0.54
     Stephenson
    0.53
     Fees
    0.53
    istle
    0.51
    mares
    0.51
     Bates
    0.51
     Pwr
    0.50
     Leilan
    0.50
    Activations Density 9.215%

    No Known Activations