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. 11938
    Prev
    Next
    INDEX
    Explanations

    terms related to muscle health and pain 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
    156
    +0.18
    1.1%
    173
    +0.12
    0.7%
    81
    +0.11
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.18
    0.01
    173
    +0.12
    0.01
    134
    +0.11
    0.01
    Negative Logits
     forthcoming
    -1.59
    llll
    -1.56
     Filed
    -1.56
     été
    -1.52
     suicide
    -1.50
     teach
    -1.49
     confidential
    -1.47
    lementary
    -1.46
    ureus
    -1.45
     prospective
    -1.45
    POSITIVE LOGITS
     strength
    1.86
    weight
    1.78
     stiffness
    1.78
    strength
    1.69
    metry
    1.62
    vation
    1.59
    walker
    1.58
     remains
    1.52
    argin
    1.51
    CAD
    1.51
    Activations Density 0.063%

    No Known Activations