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

    Neuronpedia

    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. 11826
    Prev
    Next
    INDEX
    Explanations

    positive or negative sentiments expressed in a humorous 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/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
    335
    +0.12
    0.6%
    91
    +0.11
    0.6%
    478
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.12
    0.12
    156
    +0.11
    0.13
    25
    +0.11
    0.13
    Negative Logits
    .";
    -2.52
    **_
    -2.46
    .''
    -2.32
    ."_
    -2.19
    ";
    -2.05
    à±į
    -2.01
    .""
    -2.00
    «
    -2.00
    .*;
    -1.99
    .“
    -1.99
    POSITIVE LOGITS
    )."
    4.47
    )
    4.09
    )"
    4.01
    ),
    3.99
    ?)
    3.98
    ).
    3.90
    ):
    3.87
    !)
    3.83
    )</
    3.75
     ).
    3.70
    Activations Density 1.613%

    No Known Activations