© 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. 29776
    Prev
    Next
    INDEX
    Explanations

    terms related to pharmaceuticals and biochemistry

    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
    271
    +0.20
    1.2%
    48
    +0.16
    0.9%
    159
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.20
    0.01
    66
    +0.16
    0.06
    159
    +0.16
    0.06
    Negative Logits
      ↵
    -2.33
    ↵↵
    -2.32
    ↵
    -2.32
            ↵
    -2.32
    -2.32
    -2.32
    ↵↵
    -2.32
    ↵
    -2.32
    -2.32
    <|outofrange|>
    -2.32
    POSITIVE LOGITS
    igraphy
    1.70
    ugh
    1.51
    ucky
    1.51
    ods
    1.45
     anyone
    1.41
    ãĤĩ
    1.39
    uck
    1.39
    ãĥ³
    1.37
    adelphia
    1.36
    alam
    1.34
    Activations Density 0.489%

    No Known Activations