© 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. 1079
    Prev
    Next
    INDEX
    Explanations

    verbs in present and past tense

    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
    308
    +0.05
    0.5%
    243
    +0.05
    0.5%
    514
    +0.04
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    662
    +0.05
    0.02
    55
    +0.05
    0.02
    88
    +0.04
    0.02
    Negative Logits
    iage
    -0.33
     resolutions
    -0.29
     resolution
    -0.27
     paired
    -0.27
     filib
    -0.25
    KC
    -0.25
     ali
    -0.25
    ntil
    -0.24
     appointments
    -0.24
     submar
    -0.24
    POSITIVE LOGITS
     Zup
    0.31
    ernaut
    0.28
    urden
    0.27
     Carney
    0.27
     Garner
    0.27
     Ramsey
    0.27
     Shards
    0.27
    soType
    0.27
     DAM
    0.26
    ãģĨ
    0.26
    Activations Density 0.107%

    No Known Activations