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. 29462
    Prev
    Next
    INDEX
    Explanations

    references to the music genre rock

    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
    +0.15
    0.9%
    410
    +0.13
    0.8%
    99
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    443
    +0.15
    0.02
    99
    +0.13
    0.02
    45
    +0.13
    0.01
    Negative Logits
     hers
    -1.84
     weeks
    -1.66
     suppose
    -1.62
     comment
    -1.59
     certain
    -1.54
    TRODUCTION
    -1.52
     slightest
    -1.52
     fetal
    -1.51
     wait
    -1.49
    øre
    -1.48
    POSITIVE LOGITS
    stars
    2.33
    chip
    2.02
    breaker
    1.98
    ford
    1.90
    stead
    1.87
    ings
    1.86
    cloth
    1.84
    oir
    1.83
    fulness
    1.83
    ups
    1.82
    Activations Density 0.119%

    No Known Activations