© 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. 40471
    Prev
    Next
    INDEX
    Explanations

    information related to forensic activities and procedures

    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
    +0.18
    0.9%
    393
    +0.15
    0.8%
    222
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    393
    +0.18
    0.54
    362
    +0.15
    0.30
    608
    +0.09
    0.40
    Negative Logits
    furt
    -0.66
    Course
    -0.63
    minus
    -0.58
    etheus
    -0.56
    rha
    -0.55
    È
    -0.54
    emort
    -0.54
    Ë
    -0.53
    wall
    -0.53
     âĶ
    -0.52
    POSITIVE LOGITS
     Destruction
    0.66
    senal
    0.61
    enance
    0.59
     existence
    0.58
     slain
    0.57
     controversy
    0.56
     Collider
    0.56
     Genius
    0.56
     Diseases
    0.56
     relics
    0.55
    Activations Density 31.491%

    No Known Activations