© 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. 11331
    Prev
    Next
    INDEX
    Explanations

    references to specific target metrics or goals

    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
    372
    +0.16
    0.9%
    156
    +0.15
    0.9%
    277
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    372
    +0.16
    0.02
    277
    +0.15
    0.03
    112
    +0.15
    0.02
    Negative Logits
    ĥ½
    -2.69
    ĻĤ
    -2.40
    »¿
    -1.83
    ansen
    -1.76
    Ļª
    -1.71
    §
    -1.66
    ²
    -1.66
    ¡
    -1.63
    anson
    -1.61
    itage
    -1.59
    POSITIVE LOGITS
    hole
    1.94
     sights
    1.81
    ivity
    1.79
    grounds
    1.78
    ilities
    1.78
    ting
    1.77
    ="_
    1.67
    ivities
    1.67
     areas
    1.65
     area
    1.65
    Activations Density 0.168%

    No Known Activations