© 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. 3862
    Prev
    Next
    INDEX
    Explanations

    dates and locations, particularly those related to historical events or figures

    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
    564
    +0.10
    0.6%
    169
    +0.09
    0.5%
    725
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    293
    +0.10
    0.11
    120
    +0.09
    0.10
    169
    +0.09
    0.12
    Negative Logits
    ierrez
    -0.57
    escription
    -0.56
    retty
    -0.52
    erness
    -0.51
    lehem
    -0.49
    ause
    -0.49
     Cyn
    -0.48
    footed
    -0.48
    izabeth
    -0.47
    iful
    -0.47
    POSITIVE LOGITS
     Madness
    0.59
    Ĥİ
    0.56
    ³
    0.53
    é¾įå¥ij士
    0.52
    士
    0.51
    ña
    0.51
    Pacific
    0.50
    utable
    0.49
     Dhabi
    0.48
    èª
    0.47
    Activations Density 11.531%

    No Known Activations