© 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. 892
    Prev
    Next
    INDEX
    Explanations

    IP addresses separated by dots

    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
    668
    +0.08
    0.5%
    144
    +0.08
    0.5%
    68
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.08
    0.02
    699
    +0.08
    0.01
    415
    +0.08
    0.02
    Negative Logits
    cake
    -0.56
     ital
    -0.56
    adobe
    -0.54
    heit
    -0.54
    hedon
    -0.52
    ruce
    -0.51
    rendered
    -0.50
    yout
    -0.50
    bread
    -0.50
    oys
    -0.49
    POSITIVE LOGITS
    owship
    0.64
     transmissions
    0.58
     transmission
    0.54
     footprints
    0.52
    atile
    0.52
     Networks
    0.52
     Chains
    0.51
     networks
    0.51
    algia
    0.49
    aunch
    0.48
    Activations Density 0.264%

    No Known Activations