© 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. 1-RES-SM
    11. 25199
    Prev
    Next
    INDEX
    Explanations

    terms related to the concepts of finiteness and infiniteness in mathematical contexts

    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
    156
    +0.20
    1.2%
    338
    +0.14
    0.8%
    118
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.20
    0.08
    156
    +0.14
    0.04
    271
    +0.11
    0.03
    Negative Logits
    ream
    -1.80
    inson
    -1.53
    hes
    -1.49
    ETHOD
    -1.47
    OVA
    -1.44
    drew
    -1.42
    ouch
    -1.41
    rog
    -1.40
    riev
    -1.39
    ushed
    -1.39
    POSITIVE LOGITS
    ¿½
    2.58
    ĸ
    2.35
    ļ
    2.19
    ij
    2.04
    Īĺ
    2.03
    »¿
    1.99
    ĻĤ
    1.99
    Ļ
    1.97
    £
    1.95
    ·¸
    1.92
    Activations Density 0.203%

    No Known Activations