© 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. 31335
    Prev
    Next
    INDEX
    Explanations

    computer code related to loading and unloading resources and initializing components in a program or system

    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
    708
    +0.02
    0.5%
    640
    +0.01
    0.5%
    296
    +0.01
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.02
    0.62
    393
    +0.01
    0.61
    745
    +0.01
    -0.32
    Negative Logits
    ourney
    -0.11
    âĶĢâĶĢâĶĢâĶĢ
    -0.10
    .ãĢį
    -0.10
    ãĥ´ãĤ¡
    -0.09
    cler
    -0.09
    lia
    -0.09
    -0.09
     ransom
    -0.09
    night
    -0.09
    alion
    -0.09
    POSITIVE LOGITS
    çīĪ
    0.11
    ionic
    0.10
    KB
    0.10
     tradem
    0.10
     Mehran
    0.10
    antine
    0.10
    alach
    0.10
    è¦ļéĨĴ
    0.10
    phalt
    0.10
     gast
    0.09
    Activations Density 34.640%

    No Known Activations