© 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. 27376
    Prev
    Next
    INDEX
    Explanations

    information about articles and guidelines regarding content submission and policies

    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
    82
    +0.14
    0.8%
    497
    +0.12
    0.7%
    103
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    103
    +0.14
    0.04
    329
    +0.12
    0.02
    82
    +0.11
    0.03
    Negative Logits
    ption
    -1.66
    xtures
    -1.54
    asis
    -1.54
     behaviour
    -1.52
    haviour
    -1.51
    ptions
    -1.51
    inite
    -1.50
    vent
    -1.48
    ished
    -1.46
     etc
    -1.46
    POSITIVE LOGITS
    Ĥ¬
    3.29
    Īĺ
    3.02
    º
    2.86
    ↵
    2.81
    <|outofrange|>
    2.81
    2.81
         ↵
    2.81
    <|outofrange|>
    2.81
    ↵↵
    2.81
    ↵
    2.81
    Activations Density 0.265%

    No Known Activations