© 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
    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. 4670
    Prev
    Next
    INDEX
    Explanations

    content related to financial systems, particularly focusing on the characteristics that Bitcoin should have to be legal tender

    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
    +0.29
    1.3%
    160
    +0.12
    0.5%
    472
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.29
    0.10
    512
    +0.12
    0.07
    393
    +0.10
    0.21
    Negative Logits
    isconsin
    -0.83
    rament
    -0.72
    livion
    -0.71
    rolet
    -0.66
    esses
    -0.66
     Ik
    -0.65
    chwitz
    -0.64
    ooters
    -0.62
    eful
    -0.62
    iage
    -0.62
    POSITIVE LOGITS
    nd
    1.24
    ND
    0.82
    134
    0.81
    147
    0.80
     externalToEVAOnly
    0.78
     tablespoons
    0.76
    133
    0.75
     halves
    0.73
    187
    0.73
    113
    0.72
    Activations Density 8.918%

    No Known Activations