© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27202
    Prev
    Next
    INDEX
    Explanations

    references to sales, particularly in a real estate context

    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
    376
    +0.14
    0.9%
    407
    +0.13
    0.8%
    444
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.14
    0.01
    161
    +0.13
    0.01
    417
    +0.12
    0.01
    Negative Logits
     distance
    -1.69
     married
    -1.61
     myself
    -1.57
    uran
    -1.54
     pregnant
    -1.51
    hed
    -1.45
     Honorable
    -1.43
     him
    -1.41
    ical
    -1.39
    irth
    -1.39
    POSITIVE LOGITS
    ARRAY
    1.86
    ppo
    1.80
    vist
    1.78
    ptions
    1.72
    efs
    1.68
    fal
    1.68
    fors
    1.63
    ware
    1.59
    ENTIAL
    1.57
    vre
    1.56
    Activations Density 0.011%

    No Known Activations