© 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. 29834
    Prev
    Next
    INDEX
    Explanations

    references to parsing and related coding functions

    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
    +0.18
    1.0%
    444
    +0.12
    0.7%
    392
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    173
    +0.18
    0.01
    148
    +0.12
    0.01
    376
    +0.11
    0.00
    Negative Logits
     pylori
    -1.79
    avir
    -1.56
    wards
    -1.51
    ality
    -1.48
    mighty
    -1.39
    remia
    -1.38
    ____________
    -1.37
    eks
    -1.36
    aining
    -1.33
    erculosis
    -1.32
    POSITIVE LOGITS
    ĻĤ
    1.70
    Ļª
    1.61
    İ
    1.50
    ¿½
    1.49
     consist
    1.46
    parse
    1.45
     language
    1.42
    ©
    1.42
     mind
    1.40
    mouth
    1.40
    Activations Density 0.194%

    No Known Activations