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

    Neuronpedia

    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. 4-RES-SM
    11. 12333
    Prev
    Next
    INDEX
    Explanations

    references to events, scheduling, or planning related to camps or seasons

    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
    156
    +0.38
    2.4%
    307
    +0.27
    1.7%
    306
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.38
    0.13
    145
    +0.27
    0.06
    447
    +0.14
    0.08
    Negative Logits
    amycin
    -1.96
    atory
    -1.71
    arcoma
    -1.70
    iratory
    -1.70
    ctomy
    -1.68
    iedad
    -1.62
    idone
    -1.62
    aucoma
    -1.60
    sworth
    -1.53
    ORANDUM
    -1.51
    POSITIVE LOGITS
    3.44
    ↵
    3.44
    ↵  Âł
    3.44
    ↵
    3.44
    3.44
    ↵
    3.44
    3.44
    3.44
    ↵↵
    3.44
    3.44
    Activations Density 2.446%

    No Known Activations