© 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
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 0-MLP-SM
    11. 27196
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "SM" within the text

    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
    285
    +0.13
    0.8%
    444
    +0.12
    0.7%
    392
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    285
    +0.13
    0.01
    89
    +0.12
    0.01
    444
    +0.12
    0.01
    Negative Logits
     hesitate
    -1.95
     pregnant
    -1.86
     reply
    -1.73
     authors
    -1.73
     stomach
    -1.69
     complete
    -1.66
     welcome
    -1.65
     return
    -1.64
     cry
    -1.64
     mothers
    -1.64
    POSITIVE LOGITS
    ART
    2.01
    ERC
    1.82
    edia
    1.81
     (§
    1.73
    CRO
    1.70
    DB
    1.69
    BUS
    1.68
    edi
    1.66
    DLT
    1.63
    aret
    1.61
    Activations Density 0.010%

    No Known Activations