© 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. 26082
    Prev
    Next
    INDEX
    Explanations

    references to collective identity and personal experiences shared within a community context

    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
    183
    +0.14
    0.8%
    485
    +0.13
    0.7%
    406
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    10
    +0.14
    0.00
    98
    +0.13
    0.00
    421
    +0.11
    0.00
    Negative Logits
    sburg
    -1.88
    aring
    -1.74
    izing
    -1.65
    oves
    -1.49
    gnu
    -1.47
    IDTH
    -1.45
    gow
    -1.44
    ]>
    -1.44
    wan
    -1.42
    pei
    -1.40
    POSITIVE LOGITS
    elin
    1.56
     pals
    1.48
    fet
    1.46
     claim
    1.36
    Holder
    1.35
     imagine
    1.34
    ateur
    1.31
     enough
    1.30
     automorphism
    1.30
    olev
    1.28
    Activations Density 0.002%

    No Known Activations