© 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. 8989
    Prev
    Next
    INDEX
    Explanations

    JavaScript syntax errors, specifically related to undefined variables and comparisons

    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
    +0.16
    0.9%
    126
    +0.12
    0.7%
    469
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    78
    +0.16
    -0.00
    255
    +0.12
    -0.01
    126
    +0.12
    -0.01
    Negative Logits
    aries
    -1.59
    ition
    -1.58
    ocks
    -1.49
    iest
    -1.47
    izabeth
    -1.45
    atorium
    -1.45
    gers
    -1.45
    ages
    -1.44
    quet
    -1.40
    pone
    -1.36
    POSITIVE LOGITS
    Ĵ
    2.27
    Ļ
    2.06
    ķ
    2.05
    į
    1.90
    ®
    1.90
    §
    1.76
    Ń
    1.75
    ī
    1.75
    ¤
    1.74
    Ĺ
    1.70
    Activations Density 0.342%

    No Known Activations