Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27464
    Prev
    Next
    INDEX
    Explanations

    the presence of a specific character or symbol in 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
    457
    +0.15
    0.9%
    150
    +0.12
    0.7%
    450
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    150
    +0.15
    0.03
    457
    +0.12
    0.03
    313
    +0.11
    0.03
    Negative Logits
     ?"
    -1.85
    aning
    -1.71
    ance
    -1.66
    iben
    -1.65
    }\\
    -1.62
    anc
    -1.61
    atories
    -1.59
    ancy
    -1.58
    )\\
    -1.57
    >";
    -1.54
    POSITIVE LOGITS
    ĻĤ
    1.76
    WARE
    1.59
     âĢķ
    1.59
    prep
    1.54
     punch
    1.46
    rams
    1.44
    boro
    1.42
     ethic
    1.41
     punches
    1.40
    £
    1.35
    Activations Density 1.605%

    No Known Activations