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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 12118
    Prev
    Next
    INDEX
    Explanations

    references to academic citations and authors in scholarly texts

    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
    23
    +0.14
    0.8%
    5
    +0.11
    0.6%
    271
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.14
    0.01
    23
    +0.11
    0.06
    136
    +0.11
    -0.01
    Negative Logits
    osphere
    -1.82
    itum
    -1.76
    oplasma
    -1.72
    bsd
    -1.71
    fecture
    -1.67
    =”
    -1.63
    ocide
    -1.54
    / 
    -1.53
    buntu
    -1.51
    enix
    -1.51
    POSITIVE LOGITS
     Jr
    2.44
    ĻĤ
    2.17
    Īĺ
    2.06
     Sr
    1.68
     Esq
    1.54
    ĥ
    1.45
     eds
    1.44
     author
    1.37
    ĺ
    1.36
     Asst
    1.35
    Activations Density 0.485%

    No Known Activations