© 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. 4-RES-SM
    11. 12362
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and specific study identifiers

    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/4-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.4.hook_resid_post
    Hook Layer
    4
    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
    348
    +0.17
    1.1%
    78
    +0.12
    0.7%
    157
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    136
    +0.17
    0.00
    167
    +0.12
    0.02
    157
    +0.10
    0.02
    Negative Logits
     proceeds
    -1.21
     (>
    -1.20
     Chronicle
    -1.19
    ifies
    -1.18
     returns
    -1.17
    aries
    -1.15
     *_
    -1.14
     holidays
    -1.13
     ($\
    -1.11
     _,
    -1.10
    POSITIVE LOGITS
    ı
    4.47
    Ļ
    4.25
    ↵
    4.22
    ↵
    4.22
    <|outofrange|>
    4.22
    ↵
    4.22
    4.22
                ↵
    4.22
    ↵↵
    4.22
    ↵
    4.22
    Activations Density 0.069%

    No Known Activations