© 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 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. 12555
    Prev
    Next
    INDEX
    Explanations

    elements related to legal responsibilities and actions

    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
    307
    +0.42
    2.7%
    306
    +0.12
    0.8%
    482
    +0.12
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.42
    0.17
    306
    +0.12
    0.06
    466
    +0.12
    0.12
    Negative Logits
    \])]{}
    -1.64
    )}$
    -1.60
    forth
    -1.57
    ]}$
    -1.45
    )$-
    -1.41
    )}$,
    -1.39
    ospel
    -1.39
    arijuana
    -1.39
    ')$
    -1.36
    }}$
    -1.35
    POSITIVE LOGITS
    ↵↵
    4.41
    ↵
    4.41
    ↵
    4.41
    ↵↵
    4.41
    <|outofrange|>
    4.41
    ↵
    4.41
    4.41
    4.41
     ↵
    4.41
    ↵
    4.41
    Activations Density 2.465%

    No Known Activations