© 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. 4-RES-SM
    11. 10129
    Prev
    Next
    INDEX
    Explanations

    historical dates and related information

    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
    21
    +0.18
    1.1%
    108
    +0.13
    0.8%
    185
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.18
    0.02
    308
    +0.13
    0.02
    219
    +0.10
    0.02
    Negative Logits
    "}](#
    -1.69
     ourselves
    -1.48
    .";
    -1.46
    ](
    -1.45
     respect
    -1.45
    ĻĤ
    -1.44
    .''
    -1.39
    """
    -1.37
     significantly
    -1.36
    alities
    -1.36
    POSITIVE LOGITS
    ),
    2.72
    ):
    2.33
    )_
    2.33
    )",
    2.31
    )—
    2.24
    +)
    2.20
    )',
    2.20
    ?)
    2.20
    )
    2.17
    /)
    2.12
    Activations Density 0.069%

    No Known Activations