© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14432
    Prev
    Next
    INDEX
    Explanations

    homophones or near-homophones of the word "het", specifically potentially referring to different variations of "heat"

    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
    +0.15
    0.7%
    23
    +0.13
    0.6%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.06
    326
    +0.13
    0.05
    406
    +0.10
    0.03
    Negative Logits
     reconc
    -0.61
     equ
    -0.59
    ortium
    -0.59
     kindred
    -0.58
    BuyableInstoreAndOnline
    -0.58
     chilled
    -0.55
     eternal
    -0.54
    ensical
    -0.54
     parallel
    -0.54
    vol
    -0.53
    POSITIVE LOGITS
    amines
    1.11
    te
    1.04
    ting
    1.02
    ilde
    1.02
    ty
    1.02
    ted
    0.99
    rette
    0.94
    orical
    0.92
    orically
    0.92
    ype
    0.91
    Activations Density 0.501%

    No Known Activations