© 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. 13946
    Prev
    Next
    INDEX
    Explanations

    geographical locations and related institutional references in a scientific or research 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
    +0.13
    0.7%
    481
    +0.11
    0.6%
    420
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    335
    +0.13
    0.08
    420
    +0.11
    0.11
    219
    +0.11
    0.11
    Negative Logits
    **_
    -2.72
    .''
    -2.51
    .";
    -2.32
    ."_
    -2.09
    .""
    -1.86
    «
    -1.82
    ¿½
    -1.78
    ."""
    -1.72
    `:
    -1.64
    .\"
    -1.57
    POSITIVE LOGITS
    )
    4.63
    ),
    4.63
    ).
    4.47
    )."
    4.35
    ):
    4.31
    )"
    3.98
    )—
    3.89
    )</
    3.83
    ”)
    3.79
    )[@
    3.78
    Activations Density 2.121%

    No Known Activations