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. 2-RES-SM
    6. 29271
    Prev
    Next
    INDEX
    Explanations

    references to results or output values

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    245
    +0.14
    0.8%
    365
    +0.13
    0.7%
    5
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    80
    +0.14
    0.03
    245
    +0.13
    0.03
    5
    +0.12
    0.03
    Negative Logits
    npmjs
    -2.00
    ij
    -1.77
    oxacin
    -1.73
    ]>
    -1.70
    ĥ½
    -1.69
    .""
    -1.67
    ]{.
    -1.66
    Č
    -1.61
    ¶
    -1.60
    ·¸
    -1.59
    POSITIVE LOGITS
     set
    1.66
     achievable
    1.60
    board
    1.59
    strings
    1.57
     achieved
    1.53
     result
    1.50
    atically
    1.50
    ats
    1.50
     fet
    1.49
     obtained
    1.49
    Activations Density 0.095%

    No Known Activations