© 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. 6388
    Prev
    Next
    INDEX
    Explanations

    prepositions 'along' or 'along with'

    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
    151
    +0.17
    0.6%
    526
    +0.14
    0.5%
    546
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    761
    +0.17
    0.03
    151
    +0.14
    0.03
    8
    +0.13
    0.03
    Negative Logits
    ilies
    -0.98
    orians
    -0.92
    oric
    -0.86
    iens
    -0.85
    Muslims
    -0.84
    helle
    -0.84
    orius
    -0.84
    ael
    -0.83
    aterial
    -0.83
    Rated
    -0.82
    POSITIVE LOGITS
    wagon
    1.11
    side
    0.99
    ments
    0.97
    ities
    0.96
     wagon
    0.94
    stage
    0.87
    ity
    0.85
    stairs
    0.84
    erous
    0.83
    agon
    0.82
    Activations Density 0.191%

    No Known Activations