© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 33033
    Prev
    Next
    INDEX
    Explanations

    information related to events and details in a specific historical context

    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
    68
    +0.11
    0.5%
    352
    +0.10
    0.5%
    482
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    23
    +0.11
    0.29
    154
    +0.10
    0.28
    352
    +0.09
    0.26
    Negative Logits
     decomp
    -0.82
     cloaked
    -0.72
     visibly
    -0.72
     bil
    -0.70
     physi
    -0.70
     coll
    -0.70
     visitor
    -0.69
     glide
    -0.69
     unavoid
    -0.69
     simul
    -0.69
    POSITIVE LOGITS
    elong
    0.91
    º
    0.89
    agree
    0.89
    ¯
    0.88
    ¬
    0.88
    unless
    0.87
    erest
    0.85
    save
    0.85
    ¢
    0.84
    ı
    0.81
    Activations Density 9.831%

    No Known Activations