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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 31697
    Prev
    Next
    INDEX
    Explanations

    terms related to cryptocurrency mining and scams

    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
    1.4%
    288
    +0.11
    0.5%
    17
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    17
    +0.29
    0.08
    255
    +0.11
    0.13
    453
    +0.11
    0.12
    Negative Logits
    ãĥĥãĥī
    -0.76
    ividual
    -0.72
    reve
    -0.72
    ellar
    -0.65
    bah
    -0.64
    quart
    -0.63
    ãĥĨ
    -0.62
    ghazi
    -0.62
    ãĥ£
    -0.61
    spring
    -0.60
    POSITIVE LOGITS
     techniques
    1.06
     methods
    1.00
     technologies
    0.91
     engines
    0.87
     technique
    0.86
     procedures
    0.84
     tools
    0.84
     technology
    0.84
     algorithms
    0.82
     practices
    0.80
    Activations Density 14.548%

    No Known Activations