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. 11433
    Prev
    Next
    INDEX
    Explanations

    references to media, specifically film and television

    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
    +0.20
    1.2%
    353
    +0.16
    0.9%
    176
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    353
    +0.20
    0.09
    153
    +0.16
    0.08
    271
    +0.13
    -0.04
    Negative Logits
    Funding
    -1.44
    )\].
    -1.41
     {#
    -1.41
    \].
    -1.41
     (@
    -1.35
     Entry
    -1.34
     proceeds
    -1.32
     Edge
    -1.31
    ements
    -1.30
    Fig
    -1.29
    POSITIVE LOGITS
    agus
    1.65
     hell
    1.53
    ytes
    1.45
    done
    1.43
    icos
    1.40
     heck
    1.37
    icious
    1.36
    eles
    1.35
    __)
    1.35
     kits
    1.34
    Activations Density 4.804%

    No Known Activations