Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 28839
    Prev
    Next
    INDEX
    Explanations

    mentions of authorship or copyright information

    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
    478
    +0.14
    0.8%
    53
    +0.14
    0.8%
    410
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    172
    +0.14
    0.04
    463
    +0.14
    0.03
    273
    +0.12
    0.03
    Negative Logits
    egg
    -1.54
    imetry
    -1.44
    etine
    -1.40
    ovo
    -1.39
    ectomy
    -1.37
    spot
    -1.37
     curative
    -1.36
    oret
    -1.34
    osse
    -1.34
    osite
    -1.34
    POSITIVE LOGITS
    ĥ½
    2.50
    ģ
    2.42
    Ķ
    2.22
    ·¸
    2.15
    ¬
    2.13
    ľĵ
    2.11
    ³
    2.10
    ĵ
    2.08
    İ
    2.06
    ¿
    2.01
    Activations Density 0.073%

    No Known Activations