© 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. 972
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing mentions of feedback or reactions from a group of people

    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
    585
    +0.13
    0.5%
    245
    +0.11
    0.4%
    174
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.13
    0.07
    225
    +0.11
    0.09
    222
    +0.11
    0.06
    Negative Logits
     Recon
    -0.90
     successor
    -0.85
    ebus
    -0.79
     tripod
    -0.78
    llan
    -0.76
     annex
    -0.75
    rouch
    -0.72
     reformed
    -0.72
    tein
    -0.71
     Known
    -0.71
    POSITIVE LOGITS
     submissions
    1.27
     feedback
    1.19
     ballots
    1.06
     overwhelmingly
    1.05
     testers
    1.02
     mail
    1.01
    20439
    1.01
    soType
    0.98
     applause
    0.95
     outcry
    0.93
    Activations Density 4.450%

    No Known Activations