© 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. 37223
    Prev
    Next
    INDEX
    Explanations

    phrases related to replacement or the need for a substitute

    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
    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.20
    0.9%
    624
    +0.13
    0.6%
    288
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.20
    0.20
    472
    +0.13
    0.06
    408
    +0.12
    0.12
    Negative Logits
    raq
    -0.87
    ucket
    -0.86
    jah
    -0.83
    utra
    -0.74
    omen
    -0.74
    rica
    -0.72
    ochet
    -0.71
    kers
    -0.71
    apa
    -0.71
    erest
    -0.70
    POSITIVE LOGITS
    mentation
    0.77
    aneous
    0.76
     therapies
    0.75
     therapy
    0.74
     limbs
    0.68
     replacements
    0.68
     replacement
    0.66
     candidate
    0.65
     thereof
    0.65
     casing
    0.63
    Activations Density 7.235%

    No Known Activations