© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 2-RES-SM
    11. 28751
    Prev
    Next
    INDEX
    Explanations

    medical case reports and descriptions of research studies

    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
    321
    +0.12
    0.7%
    25
    +0.11
    0.6%
    282
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    158
    +0.12
    0.05
    2
    +0.11
    0.05
    418
    +0.11
    -0.00
    Negative Logits
    "?
    -1.57
    osphere
    -1.54
     Industry
    -1.53
    nan
    -1.43
    soever
    -1.41
     solids
    -1.39
     periphery
    -1.37
    ”?
    -1.36
     crap
    -1.36
     oxides
    -1.32
    POSITIVE LOGITS
    Į
    2.41
    ↵
    2.40
    ↵
    2.40
    2.40
    ↵
    2.40
    2.40
    ↵  âĢĥ
    2.40
    <|outofrange|>
    2.40
    2.40
    č↵
    2.40
    Activations Density 0.471%

    No Known Activations