© 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 Local
    9. 6-RES_SCL-AJT
    11. 45690
    Prev
    Next
    INDEX
    Explanations

    references to gel-related technology and products

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    neuronpedia/gpt2-small__res_scl-ajt/6-res_scl-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
    578
    +0.10
    0.5%
    554
    +0.10
    0.5%
    101
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.31
    326
    +0.10
    0.24
    99
    +0.09
    0.11
    Negative Logits
    erence
    -0.67
    eries
    -0.66
    essors
    -0.65
    fman
    -0.65
    fires
    -0.64
    sight
    -0.64
    inent
    -0.64
    pring
    -0.62
    orce
    -0.62
    Ñĭ
    -0.61
    POSITIVE LOGITS
     pneum
    0.59
    TOP
    0.58
    pak
    0.57
     imaging
    0.57
    cit
    0.57
     Gillespie
    0.56
     elect
    0.55
     scissors
    0.55
    avorite
    0.54
    rine
    0.53
    Activations Density 8.188%

    No Known Activations