© 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. 9011
    Prev
    Next
    INDEX
    Explanations

    specific names or titles associated with organizations or entities

    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
    21
    +0.27
    1.7%
    306
    +0.14
    0.9%
    181
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    369
    +0.27
    0.07
    98
    +0.14
    0.06
    21
    +0.14
    0.06
    Negative Logits
    isely
    -2.09
    denly
    -1.72
    istically
    -1.59
    entially
    -1.56
    itatively
    -1.56
    fully
    -1.53
    ely
    -1.49
    imately
    -1.42
    apine
    -1.41
    }})$.
    -1.40
    POSITIVE LOGITS
    º
    3.44
    Ĵ
    3.35
    ®
    3.28
    ĨĴ
    3.16
    3.14
    č↵
    3.14
    <|outofrange|>
    3.14
    ↵
    3.14
    ↵
    3.14
    3.14
    Activations Density 1.088%

    No Known Activations