© 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. 40397
    Prev
    Next
    INDEX
    Explanations

    specific geographical locations related to institutions or places of interest

    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
    238
    +0.15
    0.6%
    288
    +0.14
    0.6%
    447
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.14
    238
    +0.14
    0.07
    752
    +0.14
    0.08
    Negative Logits
    icular
    -0.94
    icles
    -0.92
    endi
    -0.88
    icit
    -0.85
    uers
    -0.85
    acl
    -0.81
    enable
    -0.80
    roma
    -0.79
    iatrics
    -0.78
    urat
    -0.77
    POSITIVE LOGITS
     Hemisphere
    1.32
     hemisphere
    1.11
     Poverty
    1.03
    most
    0.94
    western
    0.94
     Belle
    0.90
     Railway
    0.88
     California
    0.87
     Shroud
    0.87
     States
    0.86
    Activations Density 3.612%

    No Known Activations