© 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. 29891
    Prev
    Next
    INDEX
    Explanations

    the letter 'B' 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
    369
    +0.21
    1.2%
    93
    +0.14
    0.8%
    139
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    93
    +0.21
    0.07
    369
    +0.14
    0.06
    388
    +0.12
    0.06
    Negative Logits
    Īĺ
    -2.39
    ¡
    -2.19
    ĸ´
    -2.16
    ī
    -2.14
    ¸
    -2.01
    Ĥ
    -1.99
    Ń
    -1.92
    ľĵ
    -1.88
    Ĭ
    -1.86
    ¿½
    -1.80
    POSITIVE LOGITS
    ios
    1.76
    idopsis
    1.70
    ENO
    1.67
    acter
    1.64
    HEL
    1.62
    ias
    1.61
    less
    1.60
    acillus
    1.56
    ever
    1.54
    enders
    1.53
    Activations Density 5.457%

    No Known Activations