© 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 EvalsExportsinterp-engineNEWAPI 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. 29007
    Prev
    Next
    INDEX
    Explanations

    terms related to neuroscience

    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
    156
    +0.14
    0.8%
    410
    +0.13
    0.7%
    411
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.04
    271
    +0.13
    0.01
    156
    +0.11
    0.02
    Negative Logits
    ations
    -1.67
    coming
    -1.63
    unting
    -1.54
    othing
    -1.51
    ating
    -1.46
     certain
    -1.45
    river
    -1.44
    iscuss
    -1.40
     definite
    -1.40
    ments
    -1.39
    POSITIVE LOGITS
    ī
    2.88
    ģ
    2.82
    ĨĴ
    2.80
    Ĥ
    2.76
    ·¸
    2.75
    Ĩ
    2.61
    ħ
    2.60
    ¾
    2.60
    ĭ
    2.59
    Ħ
    2.59
    Activations Density 0.178%

    No Known Activations