© 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. 27788
    Prev
    Next
    INDEX
    Explanations

    references to biting or bites 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
    164
    +0.15
    0.9%
    422
    +0.13
    0.8%
    115
    +0.13
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    422
    +0.15
    0.01
    505
    +0.13
    0.01
    164
    +0.13
    0.01
    Negative Logits
    Ĥ
    -2.87
    Ħ
    -2.77
    µ
    -2.75
    ı
    -2.69
    Ń
    -2.66
    ħ
    -2.58
    Į
    -2.58
    ³
    -2.56
    Ĺ
    -2.56
    ĵ
    -2.52
    POSITIVE LOGITS
    gart
    1.88
    strom
    1.81
    fest
    1.78
    wagen
    1.74
    indo
    1.68
    ios
    1.66
    hard
    1.63
    garten
    1.62
    fors
    1.58
     slots
    1.57
    Activations Density 0.019%

    No Known Activations