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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11590
    Prev
    Next
    INDEX
    Explanations

    expressions and structures in programming or data-related contexts

    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
    +0.16
    0.9%
    288
    +0.13
    0.7%
    479
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.16
    0.10
    309
    +0.13
    0.06
    431
    +0.13
    0.05
    Negative Logits
    abor
    -1.59
    aml
    -1.59
     herein
    -1.57
     hereinafter
    -1.53
    cephal
    -1.50
     hereafter
    -1.49
     otherwise
    -1.43
    igt
    -1.36
    angel
    -1.36
    ffic
    -1.34
    POSITIVE LOGITS
    Īĺ
    4.06
    ©
    3.70
    Ĥ¬
    3.67
    ª
    3.63
    ¼
    3.58
    ¿
    3.55
    §
    3.53
    ¿½
    3.46
    ·¸
    3.44
    ¦
    3.44
    Activations Density 0.557%

    No Known Activations