© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 26274
    Prev
    Next
    INDEX
    Explanations

    the use of the infinitive form of verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__res-sm_processed/1-res-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    standard
    Context Size
    128
    Dataset
    EleutherAI/the_pile_deduplicated
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    56
    +0.13
    0.7%
    429
    +0.12
    0.7%
    204
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    245
    +0.13
    0.00
    158
    +0.12
    0.00
    455
    +0.11
    0.00
    Negative Logits
    yline
    -1.65
    asmod
    -1.65
    bibr
    -1.59
    cept
    -1.51
    ilated
    -1.45
    imester
    -1.44
    itably
    -1.44
    ){#
    -1.42
    rå
    -1.41
    nis
    -1.40
    POSITIVE LOGITS
     maker
    1.62
    Judge
    1.52
    about
    1.38
    heric
    1.32
    ‘
    1.31
     analyst
    1.31
    rec
    1.29
    Äij
    1.27
    inder
    1.26
    orld
    1.25
    Activations Density 0.000%

    No Known Activations