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. 11476
    Prev
    Next
    INDEX
    Explanations

    information related to demographics and statistics about workforce and economic conditions

    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
    153
    +0.14
    0.8%
    143
    +0.12
    0.7%
    200
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    153
    +0.14
    0.06
    483
    +0.12
    0.10
    239
    +0.11
    0.10
    Negative Logits
    ship
    -1.76
    ¿
    -1.53
    µ
    -1.52
    ships
    -1.46
    ¹
    -1.39
     pavement
    -1.37
    coming
    -1.34
     assignments
    -1.32
    ¼
    -1.32
    º
    -1.31
    POSITIVE LOGITS
    taire
    1.60
    soever
    1.50
    arer
    1.49
    '?
    1.46
    )?
    1.45
    ________________
    1.45
    }$).
    1.44
    gest
    1.42
     sino
    1.42
    uen
    1.42
    Activations Density 2.880%

    No Known Activations