© 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. 31168
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant or important events or objects

    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
    167
    +0.19
    0.7%
    302
    +0.13
    0.5%
    565
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    565
    +0.19
    0.06
    288
    +0.13
    0.12
    219
    +0.13
    0.05
    Negative Logits
    Downloadha
    -1.19
    utics
    -1.00
    qqa
    -0.92
    lihood
    -0.92
    ople
    -0.91
    PsyNetMessage
    -0.89
    phrine
    -0.89
    tics
    -0.88
     Occupations
    -0.85
    obic
    -0.85
    POSITIVE LOGITS
    child
    1.35
    iosity
    1.24
    parent
    1.22
    eur
    1.18
    pa
    1.15
    master
    1.11
    view
    1.07
    est
    1.05
    mother
    1.04
    itud
    1.01
    Activations Density 3.544%

    No Known Activations