© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 4-RES-SM
    11. 14434
    Prev
    Next
    INDEX
    Explanations

    medical terminologies related to laboratory practices and chemical compounds

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    375
    +0.14
    0.8%
    189
    +0.13
    0.8%
    78
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.14
    -0.01
    385
    +0.13
    0.00
    129
    +0.13
    0.01
    Negative Logits
    tered
    -1.72
    deal
    -1.59
    cases
    -1.50
    ails
    -1.45
    tons
    -1.43
    ements
    -1.42
    ement
    -1.38
    ategories
    -1.38
    vement
    -1.35
    locations
    -1.35
    POSITIVE LOGITS
    ª
    2.60
    «
    2.53
    Ļ
    2.36
    ¨
    2.31
    ¸
    2.23
    °
    2.19
    Ń
    2.18
    Ķ
    2.16
    µ
    2.03
    ľĵ
    1.98
    Activations Density 0.433%

    No Known Activations