© 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. 2596
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and tweets

    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
    146
    +0.20
    0.6%
    639
    +0.14
    0.4%
    439
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.20
    0.07
    396
    +0.14
    0.06
    18
    +0.14
    0.05
    Negative Logits
    ongh
    -0.98
     thous
    -0.93
    ¿½
    -0.91
     robber
    -0.90
     pregn
    -0.89
    paio
    -0.88
    ngth
    -0.88
     plur
    -0.88
    Ī
    -0.85
    «ĺ
    -0.84
    POSITIVE LOGITS
     Referred
    1.13
    ober
    1.10
     âĶ
    1.02
     partName
    0.99
    ril
    0.96
     Became
    0.94
     08
    0.93
     PDT
    0.92
     Ãł
    0.92
     PST
    0.92
    Activations Density 0.209%

    No Known Activations