© 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. 2-MLP-SM
    11. 26122
    Prev
    Next
    INDEX
    Explanations

    expressions of certainty or emphasis in statements

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    263
    +0.14
    0.8%
    497
    +0.14
    0.8%
    356
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.14
    0.02
    15
    +0.14
    0.05
    263
    +0.12
    0.06
    Negative Logits
    inity
    -1.47
    CIAL
    -1.44
    ullah
    -1.43
    nt
    -1.42
    requent
    -1.41
    ];
    -1.40
    ussions
    -1.38
     depend
    -1.36
    atern
    -1.34
    ible
    -1.34
    POSITIVE LOGITS
    documentclass
    1.43
    yd
    1.41
     catalogue
    1.40
     aloud
    1.38
     "</
    1.38
     spins
    1.34
     slider
    1.33
    ubicin
    1.32
     further
    1.32
     edition
    1.30
    Activations Density 0.397%

    No Known Activations