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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11989
    Prev
    Next
    INDEX
    Explanations

    references to products and services related to retail and consumer goods

    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
    203
    +0.18
    1.0%
    23
    +0.14
    0.8%
    391
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.18
    0.12
    23
    +0.14
    0.12
    130
    +0.12
    0.10
    Negative Logits
    ĻĤ
    -2.22
    à±į
    -2.02
    «
    -2.00
    à±ģ
    -1.95
    àµį
    -1.93
    ariate
    -1.79
    ivo
    -1.75
    nikov
    -1.70
    nier
    -1.66
    recht
    -1.64
    POSITIVE LOGITS
    etc
    2.13
     etc
    1.86
     yes
    1.71
     especially
    1.66
    including
    1.64
    Č
    1.62
    omitempty
    1.57
    particularly
    1.57
     including
    1.56
    especially
    1.56
    Activations Density 1.042%

    No Known Activations