© 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. 27227
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "123"

    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
    314
    +0.13
    0.7%
    445
    +0.13
    0.7%
    247
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    307
    +0.13
    0.01
    445
    +0.13
    0.01
    314
    +0.12
    0.01
    Negative Logits
    rely
    -1.59
     anybody
    -1.48
    asting
    -1.48
    ?'
    -1.47
    ching
    -1.43
    "?"
    -1.42
    anned
    -1.42
    hentication
    -1.41
    usterity
    -1.39
    uppose
    -1.37
    POSITIVE LOGITS
    ®
    2.59
    ª
    2.23
    ³
    2.06
    ¾
    2.05
    º
    2.01
    °
    2.01
    neys
    1.84
    ģ
    1.83
    fried
    1.82
    ¶
    1.79
    Activations Density 0.009%

    No Known Activations