© 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. 12752
    Prev
    Next
    INDEX
    Explanations

    emotional and expressive dialogues in a conversational context

    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
    +0.07
    0.6%
    553
    +0.05
    0.5%
    218
    +0.05
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.07
    0.04
    297
    +0.05
    0.03
    596
    +0.05
    0.03
    Negative Logits
     REPL
    -0.35
    ertodd
    -0.34
     deliveries
    -0.32
     franch
    -0.32
     streetcar
    -0.32
     hosting
    -0.31
     brackets
    -0.30
    BIL
    -0.30
    oslav
    -0.30
     fixtures
    -0.30
    POSITIVE LOGITS
    bane
    0.34
    ihilation
    0.33
    IELD
    0.33
     pity
    0.33
    hov
    0.30
    zie
    0.30
     dunno
    0.29
    ortex
    0.29
     etc
    0.29
    science
    0.29
    Activations Density 0.205%

    No Known Activations