© 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 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 235
    Prev
    Next
    INDEX
    Explanations

    instances of profane language or derogatory language

    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
    288
    +0.18
    0.6%
    326
    +0.15
    0.5%
    620
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.18
    0.05
    284
    +0.15
    0.04
    738
    +0.15
    0.03
    Negative Logits
    HCR
    -1.18
    fman
    -1.11
    gary
    -0.97
    ================================
    -0.96
     Expend
    -0.96
    ocamp
    -0.96
    NetMessage
    -0.96
    ervation
    -0.92
    CVE
    -0.90
    AUT
    -0.90
    POSITIVE LOGITS
    bags
    1.27
    posts
    1.20
    storm
    1.15
    loads
    1.14
     detector
    1.14
    heads
    1.13
     detectors
    1.10
    faced
    1.08
    lords
    1.07
    lord
    1.06
    Activations Density 0.714%

    No Known Activations