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. 26752
    Prev
    Next
    INDEX
    Explanations

    questions about quantity or frequency

    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
    424
    +0.14
    0.7%
    477
    +0.12
    0.7%
    18
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    424
    +0.14
    0.03
    477
    +0.12
    0.03
    170
    +0.10
    0.02
    Negative Logits
    rified
    -1.75
    gered
    -1.70
    ically
    -1.69
    urally
    -1.60
    inated
    -1.58
    pub
    -1.58
    dog
    -1.52
    elic
    -1.51
    YPT
    -1.51
    roll
    -1.50
    POSITIVE LOGITS
    chu
    1.66
    ths
    1.53
    ktiv
    1.50
     calories
    1.46
    acity
    1.45
    boro
    1.42
     NHS
    1.38
    hurst
    1.36
    opy
    1.34
    oxacin
    1.34
    Activations Density 0.134%

    No Known Activations