© 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. 32947
    Prev
    Next
    INDEX
    Explanations

    information related to naval battles, ships, and military operations

    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
    +0.19
    0.8%
    484
    +0.10
    0.5%
    418
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    537
    +0.19
    0.10
    741
    +0.10
    0.07
    620
    +0.10
    0.03
    Negative Logits
    ãĤ±
    -0.75
    natureconservancy
    -0.73
     Hemp
    -0.71
    isoft
    -0.69
    âĶģ
    -0.68
     ingred
    -0.67
    growth
    -0.67
    rose
    -0.67
    estamp
    -0.65
    ousse
    -0.65
    POSITIVE LOGITS
     USS
    1.09
     Yamato
    1.09
     destroyer
    0.98
     squadron
    0.94
     HMS
    0.90
     stationed
    0.89
     corps
    0.89
     cruiser
    0.89
     equipped
    0.85
     warships
    0.83
    Activations Density 7.495%

    No Known Activations