© 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. 27748
    Prev
    Next
    INDEX
    Explanations

    the concept of variability or differences in various contexts

    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
    376
    +0.13
    0.7%
    417
    +0.12
    0.7%
    125
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    417
    +0.13
    0.01
    15
    +0.12
    0.01
    468
    +0.11
    0.01
    Negative Logits
    ORS
    -1.80
    UTERS
    -1.62
    orte
    -1.53
    ---|---|---
    -1.49
     slightest
    -1.45
    ollo
    -1.44
    AC
    -1.42
    glass
    -1.42
    OR
    -1.39
    coli
    -1.39
    POSITIVE LOGITS
    ĻĤ
    1.84
    Ļ
    1.77
    ually
    1.74
    Īĺ
    1.70
     sized
    1.63
    heta
    1.60
    ently
    1.57
    ħ
    1.47
    iously
    1.46
    ibus
    1.43
    Activations Density 0.356%

    No Known Activations