© 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. 27207
    Prev
    Next
    INDEX
    Explanations

    references to resources

    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
    156
    +0.25
    1.5%
    376
    +0.13
    0.8%
    365
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    163
    +0.25
    0.03
    255
    +0.13
    0.02
    365
    +0.12
    0.02
    Negative Logits
    ĥ½
    -3.13
    §
    -3.07
    Ļª
    -2.91
    ĥ
    -2.82
    ĨĴ
    -2.65
    ĩ
    -2.63
    ®
    -2.62
    ı
    -2.61
    Ń
    -2.59
    ©
    -2.58
    POSITIVE LOGITS
    ume
    1.73
     diagram
    1.67
    orbent
    1.66
    plate
    1.51
    ervation
    1.49
     evaporated
    1.47
    illar
    1.46
    Ga
    1.40
     consisted
    1.35
    erves
    1.34
    Activations Density 0.021%

    No Known Activations