© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 10449
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to gatherings or organized events for a common purpose

    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
    526
    +0.22
    0.7%
    216
    +0.19
    0.6%
    288
    +0.17
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.22
    0.09
    216
    +0.19
    0.05
    26
    +0.17
    0.06
    Negative Logits
    artment
    -1.07
    etheless
    -0.97
    andro
    -0.96
    missions
    -0.94
    incarn
    -0.90
    abol
    -0.90
    agos
    -0.90
    abilities
    -0.89
    ricular
    -0.89
    aler
    -0.89
    POSITIVE LOGITS
    isers
    1.12
     attendees
    1.08
    itud
    1.04
     bells
    1.02
    utherland
    1.01
    ãĤ¤ãĥĪ
    1.00
    iser
    1.00
    Leader
    0.99
     Rally
    0.93
     signatures
    0.92
    Activations Density 1.217%

    No Known Activations