© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. Residuals
    9. 1-RES-SM
    11. 26319
    Prev
    Next
    INDEX
    Explanations

    references to visual art and artistic expressions

    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/1-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.1.hook_resid_post
    Hook Layer
    1
    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
    189
    +0.13
    0.7%
    71
    +0.11
    0.6%
    226
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.13
    0.21
    271
    +0.11
    0.09
    156
    +0.10
    0.10
    Negative Logits
    ¶
    -2.10
    Ń
    -2.10
    ¯
    -2.06
    ©
    -2.01
    ¨
    -1.96
     adjacent
    -1.89
    ¡
    -1.88
    ¢
    -1.76
    ¿
    -1.66
    ®
    -1.65
    POSITIVE LOGITS
    isan
    2.38
    IFIC
    2.08
    illery
    1.99
    icul
    1.92
    ifice
    1.92
     history
    1.82
    ister
    1.81
    isans
    1.81
    ifacts
    1.74
    ificial
    1.74
    Activations Density 0.252%

    No Known Activations