© 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. 1-RES-SM
    11. 25360
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    53
    +0.15
    0.8%
    119
    +0.13
    0.8%
    410
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.15
    0.03
    165
    +0.13
    0.01
    106
    +0.13
    0.02
    Negative Logits
    )](
    -1.65
    \}.$$
    -1.53
    igner
    -1.51
    ERY
    -1.49
    \}\
    -1.47
    Ïķ
    -1.44
    }\}$
    -1.40
    )].
    -1.38
    rient
    -1.38
    ylon
    -1.37
    POSITIVE LOGITS
    ĻĤ
    1.91
    lee
    1.61
    tre
    1.61
    imately
    1.46
     showers
    1.42
     delinqu
    1.41
    itarian
    1.41
     dismay
    1.40
    half
    1.38
    usepackage
    1.37
    Activations Density 0.054%

    No Known Activations