© 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. 4910
    Prev
    Next
    INDEX
    Explanations

    references to digital file manipulation and security vulnerabilities

    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
    566
    +0.04
    0.6%
    326
    +0.04
    0.5%
    420
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    469
    +0.04
    0.05
    108
    +0.04
    0.07
    614
    +0.04
    0.03
    Negative Logits
    ional
    -0.26
    ulate
    -0.26
    arist
    -0.24
    ulation
    -0.24
    iola
    -0.23
    bent
    -0.22
    determination
    -0.21
    neg
    -0.21
    acion
    -0.21
    alter
    -0.21
    POSITIVE LOGITS
    CLASSIFIED
    0.30
    ById
    0.25
     illegally
    0.24
     tam
    0.23
     captcha
    0.23
    elaide
    0.23
     notor
    0.23
     aback
    0.23
    AppData
    0.22
    FactoryReloaded
    0.22
    Activations Density 14.645%

    No Known Activations