© 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. 26713
    Prev
    Next
    INDEX
    Explanations

    components and functionalities of software or applications

    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
    400
    +0.14
    0.8%
    24
    +0.12
    0.7%
    190
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    146
    +0.14
    0.10
    400
    +0.12
    0.03
    24
    +0.10
    0.13
    Negative Logits
    ķ
    -1.72
    "}](#
    -1.69
    ¸
    -1.67
    ĭ
    -1.61
    .''
    -1.61
    ŀ
    -1.60
    Ł
    -1.54
    ¿½
    -1.53
    ¨
    -1.49
    Ĥ
    -1.49
    POSITIVE LOGITS
    validation
    1.44
    roma
    1.39
     validation
    1.36
     exist
    1.34
    lication
    1.30
     scrutiny
    1.28
    reements
    1.26
    ctions
    1.26
     injection
    1.25
     careful
    1.25
    Activations Density 5.147%

    No Known Activations