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. 11878
    Prev
    Next
    INDEX
    Explanations

    terms related to cell types and their characteristics in biological research

    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
    47
    +0.18
    1.1%
    234
    +0.13
    0.8%
    441
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.18
    0.04
    432
    +0.13
    0.02
    79
    +0.12
    0.02
    Negative Logits
    ½
    -1.50
    aré
    -1.45
    gio
    -1.40
    ĻĤ
    -1.39
    ^*$
    -1.36
     mer
    -1.36
    ieurs
    -1.36
    ashi
    -1.36
    vere
    -1.36
    ikan
    -1.30
    POSITIVE LOGITS
     ---
    1.71
    encephal
    1.63
    atically
    1.58
     ----
    1.51
     shortly
    1.40
     (@
    1.39
    ership
    1.38
    encing
    1.38
     alone
    1.34
    phones
    1.34
    Activations Density 0.320%

    No Known Activations