© 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. 29904
    Prev
    Next
    INDEX
    Explanations

    various types of shapes and their properties

    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
    10
    +0.16
    0.9%
    156
    +0.13
    0.7%
    93
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.16
    0.02
    173
    +0.13
    0.01
    392
    +0.12
    0.02
    Negative Logits
    Ĥ
    -1.81
    §
    -1.80
    unnumbered
    -1.79
    ¿
    -1.71
    woke
    -1.69
    ľĵ
    -1.66
     behalf
    -1.61
    ĸ´
    -1.60
    oday
    -1.57
    ļ
    -1.55
    POSITIVE LOGITS
    ahead
    2.11
    makers
    1.77
    imetry
    1.72
    print
    1.68
    idable
    1.67
    faces
    1.65
    imetric
    1.63
     (\<
    1.61
    maker
    1.58
    bys
    1.54
    Activations Density 0.103%

    No Known Activations