© 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. 9299
    Prev
    Next
    INDEX
    Explanations

    structured data representations and configuration details

    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
    82
    +0.15
    0.8%
    397
    +0.12
    0.7%
    29
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    82
    +0.15
    0.07
    325
    +0.12
    0.10
    397
    +0.11
    0.07
    Negative Logits
    ”).
    -2.15
    ”)
    -1.97
    ”),
    -1.79
    .”).
    -1.77
    oretic
    -1.64
     ”
    -1.56
     ‘
    -1.56
    "));
    -1.54
    .”
    -1.53
    ?”
    -1.52
    POSITIVE LOGITS
    }
    3.89
    ĭ
    3.82
    ı
    3.73
    §
    3.71
    ¿
    3.62
     }
    3.54
    ¸
    3.53
    ł
    3.51
    Ĵ
    3.49
    Ħ
    3.46
    Activations Density 0.946%

    No Known Activations