© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 10492
    Prev
    Next
    INDEX
    Explanations

    phrases related to security vulnerabilities and software updates in technology news articles

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scefr-ajt/6-res_scefr-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
    7
    +0.14
    0.5%
    504
    +0.13
    0.5%
    11
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.14
    0.21
    326
    +0.13
    0.17
    220
    +0.12
    0.12
    Negative Logits
    acular
    -0.92
    igm
    -0.79
    orative
    -0.79
    aution
    -0.77
    amination
    -0.77
    ision
    -0.77
    isions
    -0.75
    Downloadha
    -0.73
    ICE
    -0.72
     instr
    -0.72
    POSITIVE LOGITS
    ospital
    0.93
    arrison
    0.93
    alo
    0.90
    ancock
    0.88
    ISTORY
    0.88
    ness
    0.87
    ttp
    0.87
    aday
    0.85
    idays
    0.85
    moon
    0.85
    Activations Density 4.901%

    No Known Activations