© 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. 40371
    Prev
    Next
    INDEX
    Explanations

    elements related to computer graphics, shaders and textures in a document, potentially looking for specific technical details

    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
    578
    +0.08
    0.5%
    7
    +0.08
    0.5%
    216
    +0.08
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.08
    0.21
    709
    +0.08
    0.11
    99
    +0.08
    0.09
    Negative Logits
    tsky
    -0.60
    ento
    -0.51
    ILY
    -0.51
    ership
    -0.50
    STON
    -0.50
    lett
    -0.50
    estic
    -0.50
    hyde
    -0.47
    tainment
    -0.47
    kins
    -0.47
    POSITIVE LOGITS
    cil
    0.59
    ript
    0.55
    burgh
    0.55
    alkyrie
    0.53
    asio
    0.50
     vert
    0.49
    ided
    0.49
    ected
    0.49
    uart
    0.48
    olkien
    0.47
    Activations Density 7.390%

    No Known Activations