© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 25992
    Prev
    Next
    INDEX
    Explanations

    actions related to modifying or publishing software

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    173
    +0.14
    0.7%
    316
    +0.13
    0.7%
    109
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    109
    +0.14
    0.01
    470
    +0.13
    0.02
    316
    +0.12
    0.02
    Negative Logits
    Ĺ
    -3.82
    ®
    -3.46
    ¯
    -3.39
    ¦
    -3.26
    §
    -3.24
    ¹
    -3.24
    ³
    -3.22
    ĵ
    -3.16
    ľ
    -3.14
    Ĥ
    -3.12
    POSITIVE LOGITS
     them
    1.74
     modo
    1.72
     control
    1.56
     field
    1.54
     fields
    1.50
     disse
    1.44
     itself
    1.42
     discipline
    1.40
     himself
    1.39
     equation
    1.38
    Activations Density 0.103%

    No Known Activations