© 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. 5742
    Prev
    Next
    INDEX
    Explanations

    technical terms related to software development and technical processes

    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
    396
    +0.15
    0.5%
    491
    +0.14
    0.5%
    50
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.21
    651
    +0.14
    0.11
    195
    +0.13
    0.01
    Negative Logits
     Beautiful
    -0.97
    hyde
    -0.93
    arenthood
    -0.91
    noxious
    -0.88
    ensis
    -0.86
    ukong
    -0.85
    ulhu
    -0.84
    entric
    -0.82
    kef
    -0.81
    isine
    -0.81
    POSITIVE LOGITS
    soType
    1.18
    statement
    1.06
    license
    0.98
    fledged
    0.96
    escription
    0.95
    vertisement
    0.94
    endum
    0.93
    table
    0.92
    cknowled
    0.91
    shoot
    0.90
    Activations Density 4.690%

    No Known Activations