© 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. 7658
    Prev
    Next
    INDEX
    Explanations

    complimentary phrases expressing appreciation and admiration

    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
    496
    +0.03
    0.4%
    649
    +0.03
    0.4%
    750
    +0.03
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.03
    0.03
    614
    +0.03
    0.03
    616
    +0.03
    0.03
    Negative Logits
     impuls
    -0.23
     preceded
    -0.21
     suffice
    -0.21
     collapsed
    -0.21
     Fas
    -0.21
     unilaterally
    -0.21
     plummeted
    -0.21
     abruptly
    -0.21
     flashed
    -0.21
     disclaim
    -0.20
    POSITIVE LOGITS
    ohan
    0.28
    ĺħ
    0.28
    atching
    0.24
    atch
    0.24
    Versions
    0.23
    thood
    0.23
    00200000
    0.22
    «ĺ
    0.22
    isodes
    0.22
    urt
    0.22
    Activations Density 0.056%

    No Known Activations