© 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. 10180
    Prev
    Next
    INDEX
    Explanations

    directives related to editing or modifying content

    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
    78
    +0.18
    1.0%
    397
    +0.17
    1.0%
    260
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.18
    -0.00
    157
    +0.17
    0.03
    260
    +0.12
    0.03
    Negative Logits
    etric
    -1.68
    atinib
    -1.59
    nell
    -1.59
    atra
    -1.57
    nos
    -1.51
    azole
    -1.50
    ationally
    -1.49
    onica
    -1.49
    otherapy
    -1.43
    eered
    -1.43
    POSITIVE LOGITS
     THIS
    1.81
     GENERATED
    1.72
    ++
    1.63
     -*-
    1.57
     FILE
    1.55
     BLOCK
    1.47
    Ñĭ
    1.44
     LIABILITY
    1.44
    __.
    1.39
     *.
    1.37
    Activations Density 0.121%

    No Known Activations