© 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
    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. 4143
    Prev
    Next
    INDEX
    Explanations

    phrases related to healthcare, medical institutions, and legal matters

    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
    575
    +0.17
    0.6%
    302
    +0.14
    0.5%
    735
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.17
    0.06
    394
    +0.14
    0.06
    26
    +0.14
    0.08
    Negative Logits
    rawdownloadcloneembedreportprint
    -0.97
    ktop
    -0.88
    chenko
    -0.83
    NVIDIA
    -0.81
    utra
    -0.81
    udeau
    -0.80
     sled
    -0.78
     bre
    -0.78
    vati
    -0.77
    imura
    -0.77
    POSITIVE LOGITS
     Degree
    1.02
     Station
    0.99
    hurst
    0.97
    Grade
    0.96
     Chapel
    0.96
    ritch
    0.95
     Dublin
    0.94
    house
    0.94
    stown
    0.92
    Hum
    0.92
    Activations Density 4.287%

    No Known Activations