© 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. 10790
    Prev
    Next
    INDEX
    Explanations

    references to mathematical terms or code concepts related to base and numerical relationships

    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
    +0.21
    0.7%
    549
    +0.18
    0.6%
    270
    +0.15
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    21
    +0.21
    0.04
    288
    +0.18
    0.05
    549
    +0.15
    0.04
    Negative Logits
    icut
    -1.27
    estern
    -1.18
    oso
    -1.12
    apes
    -1.11
    NESS
    -1.08
    ansen
    -1.06
    icer
    -1.06
    istor
    -1.06
    alid
    -1.05
    ulp
    -1.03
    POSITIVE LOGITS
    camp
    1.65
    plate
    1.45
    plates
    1.38
    band
    1.17
     erosion
    1.15
    ball
    1.12
     DF
    1.04
    itaire
    1.03
    plane
    1.03
    rame
    1.02
    Activations Density 0.781%

    No Known Activations