© 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. 36322
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer malware and cybersecurity

    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
    0.9%
    496
    +0.13
    0.6%
    183
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    447
    +0.19
    0.19
    138
    +0.13
    0.17
    649
    +0.12
    0.04
    Negative Logits
    è¦ļéĨĴ
    -0.81
    éĥ
    -0.78
    BILITY
    -0.74
    代
    -0.73
    ILY
    -0.72
    astically
    -0.69
     basis
    -0.69
    å£
    -0.68
    utical
    -0.67
    iddled
    -0.67
    POSITIVE LOGITS
    ership
    0.96
    ert
    0.94
    erton
    0.93
    ward
    0.89
    spring
    0.87
    ers
    0.86
     Deck
    0.86
    er
    0.84
     Away
    0.84
     Limits
    0.84
    Activations Density 7.729%

    No Known Activations