© 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. 13084
    Prev
    Next
    INDEX
    Explanations

    phrases related to insults and criticisms

    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
    +0.22
    0.8%
    285
    +0.15
    0.5%
    326
    +0.14
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.11
    326
    +0.15
    0.09
    526
    +0.14
    -0.00
    Negative Logits
    negie
    -1.01
    arijuana
    -1.00
    ulhu
    -0.98
    ramid
    -0.97
    ortex
    -0.96
    arten
    -0.96
    ills
    -0.94
    arez
    -0.94
    enfranch
    -0.94
    ello
    -0.93
    POSITIVE LOGITS
    ingly
    1.10
     Gaw
    1.08
     insult
    1.07
    faced
    1.05
     disrespect
    1.04
    fully
    1.03
     caric
    1.02
    ously
    1.00
     insults
    1.00
     Honour
    0.99
    Activations Density 1.313%

    No Known Activations