© 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. 12405
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific terms related to calculations, formulas and analytical methods

    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
    447
    +0.16
    0.5%
    359
    +0.13
    0.4%
    730
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    314
    +0.16
    0.01
    160
    +0.13
    0.08
    699
    +0.13
    0.03
    Negative Logits
    avascript
    -1.00
    ebus
    -0.99
    ety
    -0.96
    uese
    -0.96
    ahoo
    -0.95
    enne
    -0.93
    glers
    -0.89
     scripting
    -0.89
    ounge
    -0.89
    unky
    -0.88
    POSITIVE LOGITS
    âĪ
    1.35
     âĪ
    1.35
    λ
    1.30
     [(
    1.27
     μ
    1.21
    β
    1.20
     ÎĶ
    1.17
    Î
    1.16
    âĪĴ
    1.15
     Î
    1.15
    Activations Density 1.195%

    No Known Activations