© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. Residuals
    5. 2-RES-SM
    6. 29808
    Prev
    Next
    INDEX
    Explanations

    terms associated with cancer and tumor classification

    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
    156
    +0.26
    1.6%
    186
    +0.12
    0.7%
    505
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    304
    +0.26
    0.01
    505
    +0.12
    0.01
    148
    +0.12
    0.00
    Negative Logits
     hers
    -1.80
    clusive
    -1.75
    pinion
    -1.64
    ori
    -1.64
     dedicated
    -1.54
     careful
    -1.51
     appropriate
    -1.50
     convenient
    -1.49
     updated
    -1.49
     yours
    -1.42
    POSITIVE LOGITS
    £
    4.33
    ĻĤ
    4.30
    Ļª
    4.30
    Ĵ
    4.27
    °
    4.16
    ĩ
    4.09
    Ł
    4.06
    ¼
    4.05
    ·
    4.02
    ĸ
    3.99
    Activations Density 0.053%

    No Known Activations