© 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. 30264
    Prev
    Next
    INDEX
    Explanations

    instances of the term "subtitles."

    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
    111
    +0.14
    0.8%
    376
    +0.13
    0.7%
    59
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    111
    +0.14
    0.01
    264
    +0.13
    0.01
    59
    +0.12
    0.01
    Negative Logits
    ľĵ
    -1.82
    eer
    -1.82
    »¿
    -1.82
    Ļª
    -1.68
    vere
    -1.63
    ĸ´
    -1.55
    ureus
    -1.55
    §
    -1.53
    ¢
    -1.47
    tm
    -1.44
    POSITIVE LOGITS
    ]",
    1.65
    otal
    1.61
     embargo
    1.57
     flown
    1.47
     awarded
    1.46
     shutdown
    1.45
    angu
    1.40
    !”
    1.38
     lineup
    1.33
    ]'
    1.32
    Activations Density 0.014%

    No Known Activations