© 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. 31456
    Prev
    Next
    INDEX
    Explanations

    words related to events, locations, and product/service promotions

    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
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    447
    +0.11
    0.7%
    7
    +0.09
    0.6%
    620
    +0.07
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.19
    288
    +0.09
    0.18
    620
    +0.07
    0.02
    Negative Logits
    paste
    -0.52
    ethical
    -0.48
    raught
    -0.48
    involved
    -0.45
    ogyn
    -0.45
    gnu
    -0.44
    agents
    -0.44
    ISO
    -0.43
     Dram
    -0.43
    available
    -0.43
    POSITIVE LOGITS
    aic
    0.71
    ione
    0.55
    laus
    0.54
    usa
    0.52
    itol
    0.52
    angelo
    0.51
    amped
    0.50
    iated
    0.50
    mers
    0.50
    estation
    0.49
    Activations Density 6.376%

    No Known Activations