© 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. 27695
    Prev
    Next
    INDEX
    Explanations

    terms related to bandwidth and throughput

    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
    +0.15
    0.9%
    115
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.25
    0.01
    156
    +0.15
    0.01
    120
    +0.12
    0.01
    Negative Logits
     pleasure
    -1.73
     git
    -1.59
    ureus
    -1.58
     blessing
    -1.43
    cca
    -1.43
     Calendar
    -1.41
     help
    -1.40
    usepackage
    -1.40
     whom
    -1.39
    woke
    -1.39
    POSITIVE LOGITS
    worth
    1.97
    gap
    1.70
    wise
    1.70
    ontal
    1.60
    block
    1.55
    neutral
    1.55
     spectrum
    1.53
    "}](#
    1.48
    furt
    1.45
    worthy
    1.43
    Activations Density 0.021%

    No Known Activations