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. 11559
    Prev
    Next
    INDEX
    Explanations

    code-related terms and components

    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
    12
    +0.19
    1.1%
    293
    +0.14
    0.9%
    229
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    12
    +0.19
    0.14
    293
    +0.14
    0.11
    337
    +0.13
    0.06
    Negative Logits
    ľĵ
    -1.73
    ŀ
    -1.49
    punk
    -1.37
    §
    -1.36
    uple
    -1.34
    ·
    -1.33
    ļ
    -1.32
     kick
    -1.30
    psin
    -1.30
    Ĥ¬
    -1.25
    POSITIVE LOGITS
    ings
    1.58
    liography
    1.54
    journals
    1.49
    ncbi
    1.48
     families
    1.46
    STA
    1.44
    :**
    1.39
    artments
    1.37
    usalem
    1.37
    BH
    1.37
    Activations Density 3.850%

    No Known Activations