© 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. 31229
    Prev
    Next
    INDEX
    Explanations

    terms related to space exploration and activities related to it, such as rocketry, satellite launches, and space technology advancements

    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
    413
    +0.10
    0.6%
    684
    +0.07
    0.4%
    251
    +0.07
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.10
    -0.14
    284
    +0.07
    0.11
    659
    +0.07
    0.10
    Negative Logits
    hower
    -0.61
     EDITION
    -0.57
    REDACTED
    -0.57
    inventoryQuantity
    -0.56
    soType
    -0.53
    giving
    -0.52
     inaug
    -0.52
     endowed
    -0.52
     sher
    -0.51
    terday
    -0.51
    POSITIVE LOGITS
    yna
    0.71
    olini
    0.63
    idi
    0.62
    hett
    0.60
    odan
    0.59
    ahl
    0.59
    onga
    0.58
    antz
    0.58
    merga
    0.58
    illa
    0.58
    Activations Density 6.361%

    No Known Activations