© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3960
    Prev
    Next
    INDEX
    Explanations

    technical and complex terms related to mathematics, technology, 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
    549
    +0.07
    0.6%
    659
    +0.05
    0.5%
    93
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    70
    +0.07
    0.11
    493
    +0.05
    0.07
    549
    +0.05
    0.07
    Negative Logits
    ãĥĦ
    -0.42
    isations
    -0.41
    izations
    -0.41
    oppable
    -0.41
    é¾įå
    -0.40
    icro
    -0.36
    士
    -0.36
    nesota
    -0.36
    ÏĦ
    -0.36
    ä¸
    -0.35
    POSITIVE LOGITS
    enne
    0.54
     Cay
    0.47
    uga
    0.47
    apeake
    0.45
    olla
    0.42
    xon
    0.41
     Johnston
    0.41
    adian
    0.39
     Springs
    0.38
    esian
    0.36
    Activations Density 9.140%

    No Known Activations