© 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. 27666
    Prev
    Next
    INDEX
    Explanations

    specific formatting or code syntax

    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
    444
    +0.14
    0.8%
    71
    +0.13
    0.7%
    457
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.14
    0.02
    404
    +0.13
    0.01
    111
    +0.12
    0.01
    Negative Logits
    acular
    -1.91
    naments
    -1.81
    akers
    -1.69
    urope
    -1.68
    rica
    -1.66
    igated
    -1.58
    argin
    -1.56
    tering
    -1.55
    chers
    -1.52
    pering
    -1.49
    POSITIVE LOGITS
    £
    2.06
    ¥
    1.95
    Ļ
    1.93
    Ĵ
    1.89
    §
    1.82
    ·
    1.69
    ĺ
    1.69
    į
    1.67
    ¤
    1.67
    Ĩ
    1.66
    Activations Density 0.013%

    No Known Activations