© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 28286
    Prev
    Next
    INDEX
    Explanations

    imperative verbs or actions being suggested in the text

    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
    503
    +0.14
    0.8%
    60
    +0.13
    0.7%
    492
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    485
    +0.14
    0.14
    486
    +0.13
    0.11
    170
    +0.13
    0.09
    Negative Logits
     emphasis
    -1.73
    appropriate
    -1.51
    undry
    -1.45
    continuous
    -1.44
    arate
    -1.43
    heries
    -1.43
    filling
    -1.40
    athed
    -1.39
    ircraft
    -1.39
    unreadable
    -1.38
    POSITIVE LOGITS
    "?
    1.77
    ]'
    1.67
    [/
    1.55
    ]}
    1.54
    '?
    1.52
    ”?
    1.50
    ität
    1.46
    }}'
    1.44
     abroad
    1.44
    '?"
    1.42
    Activations Density 0.191%

    No Known Activations