© 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. 39812
    Prev
    Next
    INDEX
    Explanations

    HTML code snippets with specific attributes and structures

    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
    766
    +0.06
    0.6%
    435
    +0.05
    0.5%
    492
    +0.05
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.06
    0.31
    373
    +0.05
    -0.24
    6
    +0.05
    0.16
    Negative Logits
     coinc
    -0.33
     jeopardy
    -0.32
    gey
    -0.32
     firsthand
    -0.32
     chances
    -0.31
    crit
    -0.30
     visions
    -0.30
     accelerated
    -0.29
    iolet
    -0.29
     rebound
    -0.29
    POSITIVE LOGITS
    ########
    0.34
    Configuration
    0.33
    CSS
    0.32
    lees
    0.32
     Calling
    0.32
    ĺħ
    0.32
     ###
    0.31
    Library
    0.31
    Ø©
    0.31
    Domain
    0.31
    Activations Density 13.332%

    No Known Activations