© 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. 8685
    Prev
    Next
    INDEX
    Explanations

    positive sentiment and admiration towards certain qualities or behaviors

    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
    515
    +0.21
    0.8%
    649
    +0.19
    0.7%
    526
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.21
    0.08
    555
    +0.19
    0.06
    288
    +0.15
    0.09
    Negative Logits
    loo
    -1.27
    HAEL
    -0.96
    tracks
    -0.92
    ARD
    -0.91
    æĸ¹
    -0.90
    stall
    -0.90
    ONEY
    -0.90
    ORGE
    -0.89
    ctica
    -0.87
    phal
    -0.87
    POSITIVE LOGITS
    itional
    1.69
    itions
    1.46
    itivity
    1.39
    ited
    1.28
    itives
    1.25
    sembly
    1.24
    idon
    1.23
    iting
    1.20
    essions
    1.20
    itive
    1.20
    Activations Density 1.163%

    No Known Activations