© 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. 29499
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term 'ANG'

    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
    385
    +0.11
    0.6%
    376
    +0.11
    0.6%
    276
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    263
    +0.11
    0.01
    134
    +0.11
    0.01
    385
    +0.10
    0.01
    Negative Logits
    >';
    -1.47
     prompt
    -1.45
    structor
    -1.44
    heres
    -1.43
    >`
    -1.40
     investigators
    -1.39
    hes
    -1.38
    rceil
    -1.37
     \%
    -1.37
    cess
    -1.34
    POSITIVE LOGITS
    ULAR
    1.82
    kok
    1.78
    recht
    1.75
    esan
    1.74
     platforms
    1.67
    enstein
    1.64
    illard
    1.64
     platform
    1.61
    ulation
    1.61
    ycin
    1.61
    Activations Density 0.082%

    No Known Activations