© 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. 45735
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering systems

    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
    +0.32
    1.4%
    288
    +0.17
    0.8%
    527
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    527
    +0.32
    0.06
    575
    +0.17
    0.13
    274
    +0.13
    0.09
    Negative Logits
    ishable
    -0.82
    onga
    -0.81
    urous
    -0.76
    bow
    -0.75
    furt
    -0.71
    tein
    -0.68
    æĢ
    -0.68
    past
    -0.67
    erenn
    -0.66
    ãĥĥ
    -0.66
    POSITIVE LOGITS
    atics
    1.13
     integ
    1.02
    atically
    0.96
     architectures
    0.92
     systems
    0.86
    ologies
    0.84
    wide
    0.84
    atic
    0.83
     administrator
    0.82
     overload
    0.81
    Activations Density 8.032%

    No Known Activations