© 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. 32007
    Prev
    Next
    INDEX
    Explanations

    technical specifications and parameters related to computing or software

    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
    312
    +0.13
    0.7%
    176
    +0.13
    0.7%
    240
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.13
    0.18
    160
    +0.13
    0.16
    492
    +0.12
    0.10
    Negative Logits
    ounger
    -1.68
    Foundation
    -1.51
    \]]{}
    -1.49
    stown
    -1.47
    yss
    -1.45
    NAP
    -1.42
    foot
    -1.41
    uten
    -1.41
    nae
    -1.40
    bie
    -1.37
    POSITIVE LOGITS
    ![**
    2.15
     conventions
    1.74
    polymers
    1.45
    ulations
    1.42
    ![
    1.36
    izations
    1.31
    };
    1.31
     dispositions
    1.31
    ificate
    1.30
    isations
    1.30
    Activations Density 8.100%

    No Known Activations