© 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 E2E Recon
    9. 6-RES_SCEFR-AJT
    11. 7207
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a sense of urgency or immediate action

    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
    393
    +0.20
    0.7%
    348
    +0.19
    0.6%
    237
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    632
    +0.20
    0.04
    564
    +0.19
    0.04
    582
    +0.17
    0.03
    Negative Logits
    Nap
    -1.26
    yne
    -1.02
    transfer
    -0.98
    rine
    -0.98
    rosc
    -0.97
    nostic
    -0.96
    mos
    -0.95
    alls
    -0.93
    Recomm
    -0.93
    heimer
    -0.92
    POSITIVE LOGITS
     practicable
    1.05
     possible
    1.04
    auga
    0.91
    afort
    0.90
    aunder
    0.86
     Blow
    0.86
     Jindal
    0.85
     Shots
    0.83
     Carm
    0.81
    semb
    0.79
    Activations Density 0.384%

    No Known Activations