© 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. 1069
    Prev
    Next
    INDEX
    Explanations

    phrases related to urgent or critical situations

    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
    389
    +0.20
    0.6%
    746
    +0.20
    0.6%
    119
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    746
    +0.20
    0.05
    23
    +0.20
    0.07
    129
    +0.13
    0.05
    Negative Logits
    glers
    -1.38
    Reviewer
    -1.30
    hetti
    -1.08
    enhagen
    -1.07
    regor
    -1.02
    ancial
    -1.02
     Kinnikuman
    -0.92
    zzi
    -0.90
    trak
    -0.89
    enthal
    -0.88
    POSITIVE LOGITS
    perate
    1.62
     Moines
    1.58
    criptions
    1.57
    ync
    1.56
    erve
    1.48
    cend
    1.48
    cribed
    1.32
    erving
    1.32
    itant
    1.31
    ktop
    1.30
    Activations Density 1.305%

    No Known Activations