© 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. 2-RES-SM
    11. 12957
    Prev
    Next
    INDEX
    Explanations

    unique identifiers and properties in different datasets or records

    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/2-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.2.hook_resid_post
    Hook Layer
    2
    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
    20
    +0.13
    0.7%
    499
    +0.12
    0.7%
    360
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    20
    +0.13
    0.13
    7
    +0.12
    -0.01
    168
    +0.12
    0.06
    Negative Logits
    ±
    -1.61
    aline
    -1.58
    ĨĴ
    -1.53
    alin
    -1.50
    enne
    -1.49
    ľĵ
    -1.45
    ©
    -1.44
    ĸ
    -1.43
    ¢
    -1.41
    antine
    -1.41
    POSITIVE LOGITS
    ETHOD
    1.79
    ylum
    1.55
    governmental
    1.53
    acity
    1.46
    cludes
    1.43
    ctrine
    1.42
    ...](
    1.39
    Ps
    1.34
    edes
    1.32
    reth
    1.32
    Activations Density 3.762%

    No Known Activations