© 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. 28659
    Prev
    Next
    INDEX
    Explanations

    numerical data points or metrics

    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
    151
    +0.12
    0.6%
    425
    +0.11
    0.6%
    374
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.12
    0.01
    221
    +0.11
    0.01
    374
    +0.10
    0.01
    Negative Logits
     Imm
    -1.42
    herin
    -1.42
     enough
    -1.41
    hes
    -1.40
    ently
    -1.39
     respectively
    -1.36
    thood
    -1.35
     tree
    -1.33
    isc
    -1.30
    ron
    -1.29
    POSITIVE LOGITS
    RSOS
    1.77
    {|
    1.74
    RSP
    1.67
    IJ
    1.49
    Defendant
    1.44
    ––––––––
    1.42
     boil
    1.41
    Returns
    1.37
    ésident
    1.34
    etted
    1.33
    Activations Density 0.020%

    No Known Activations