© 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. 27705
    Prev
    Next
    INDEX
    Explanations

    the superlative form of adjectives

    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
    81
    +0.15
    0.9%
    409
    +0.12
    0.7%
    274
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    409
    +0.15
    0.01
    81
    +0.12
    0.01
    237
    +0.11
    0.01
    Negative Logits
    Ĭ
    -1.83
    ±
    -1.79
    ¦
    -1.78
    TY
    -1.75
    §
    -1.71
    ®
    -1.70
    º
    -1.69
    ©
    -1.59
    't
    -1.57
    ·¸
    -1.51
    POSITIVE LOGITS
    aceae
    1.76
    ière
    1.65
     quart
    1.59
    ager
    1.57
    ÅĪ
    1.50
    gren
    1.49
     econó
    1.47
     imagin
    1.43
     Americans
    1.42
    iberal
    1.42
    Activations Density 1.590%

    No Known Activations