© 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. MLP Post
    9. 0-MLP-SM
    11. 26022
    Prev
    Next
    INDEX
    Explanations

    instances of the term 'visual' and related visual concepts in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ctigges/pythia-70m-deduped__mlp-sm_processed/0-mlp-sm
    Prompts (Dashboard)
    32,768 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    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
    +0.23
    1.4%
    470
    +0.17
    1.0%
    148
    +0.14
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    470
    +0.23
    0.03
    192
    +0.17
    0.02
    121
    +0.14
    0.02
    Negative Logits
     Online
    -1.42
     alive
    -1.42
    vere
    -1.39
     salmon
    -1.38
    uge
    -1.36
     EPA
    -1.35
    uke
    -1.30
    ophageal
    -1.30
     exponentially
    -1.30
    rocy
    -1.27
    POSITIVE LOGITS
    idades
    2.12
    izations
    1.72
    isations
    1.71
    films
    1.67
    film
    1.64
    "}](#
    1.61
    idad
    1.60
    idade
    1.58
    izing
    1.55
    processing
    1.52
    Activations Density 0.041%

    No Known Activations