© 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. 27709
    Prev
    Next
    INDEX
    Explanations

    occurrences of high-frequency numerical values or marks

    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
    198
    +0.13
    0.7%
    440
    +0.13
    0.7%
    268
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.13
    0.40
    53
    +0.13
    0.42
    56
    +0.11
    0.11
    Negative Logits
    ģ
    -2.01
    ĭ
    -1.99
    ĥ½
    -1.91
    Ķ
    -1.90
    Ĩ
    -1.84
    ħ
    -1.81
    ½
    -1.80
    ±
    -1.79
    ¿
    -1.74
    ķ
    -1.74
    POSITIVE LOGITS
    onents
    1.73
    ers
    1.71
    enger
    1.71
    however
    1.68
    age
    1.65
    isher
    1.63
    quire
    1.62
    soever
    1.60
    ership
    1.59
    itive
    1.56
    Activations Density 4.670%

    No Known Activations