Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 1-RES-SM
    6. 26717
    Prev
    Next
    INDEX
    Explanations

    HTTP methods related to web requests

    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
    214
    +0.13
    0.7%
    148
    +0.12
    0.7%
    254
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.13
    0.01
    386
    +0.12
    0.02
    351
    +0.11
    0.02
    Negative Logits
    rely
    -2.10
    ially
    -1.89
    ously
    -1.89
    acial
    -1.81
    inally
    -1.80
    respectively
    -1.74
    oles
    -1.72
    ĥ½
    -1.70
    other
    -1.69
    reduc
    -1.67
    POSITIVE LOGITS
    erior
    1.82
    ER
    1.64
    TRA
    1.58
    PLIED
    1.52
     oper
    1.51
    CRIPT
    1.51
    érie
    1.48
    enezuel
    1.48
    ledge
    1.44
    MAN
    1.44
    Activations Density 0.140%

    No Known Activations