© 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. 9293
    Prev
    Next
    INDEX
    Explanations

    code snippets or programming constructs related to data processing and algorithms

    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
    332
    +0.14
    0.8%
    78
    +0.14
    0.7%
    178
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    332
    +0.14
    0.12
    78
    +0.14
    0.00
    27
    +0.11
    0.10
    Negative Logits
     you
    -2.06
     âĢ¢
    -1.71
    ").
    -1.71
    ");
    -1.68
    ”),
    -1.63
    ”).
    -1.61
    ”)
    -1.53
    "),
    -1.51
    .");
    -1.51
    you
    -1.51
    POSITIVE LOGITS
    ]
    5.54
    ]_
    5.00
    ]:
    4.97
    ]."
    4.95
    ]=
    4.94
    ]{.
    4.93
    ](
    4.89
    ].
    4.85
    ']
    4.84
    ][
    4.83
    Activations Density 1.461%

    No Known Activations