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

    Neuronpedia

    Jacobian LensNEW
    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. 29106
    Prev
    Next
    INDEX
    Explanations

    terms related to cumulative effects or accumulative processes

    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
    +0.19
    1.1%
    376
    +0.13
    0.7%
    380
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    444
    +0.19
    0.01
    204
    +0.13
    0.01
    265
    +0.13
    0.01
    Negative Logits
    obby
    -1.55
    acking
    -1.54
     fair
    -1.51
    aming
    -1.48
    acial
    -1.45
    uge
    -1.43
    ÑĢан
    -1.42
    .);
    -1.36
    éri
    -1.34
    orth
    -1.32
    POSITIVE LOGITS
    ités
    2.01
    iating
    1.67
    ussions
    1.66
    iations
    1.65
    entially
    1.51
    itating
    1.48
    issions
    1.47
    ulence
    1.47
    itate
    1.46
    reon
    1.44
    Activations Density 0.019%

    No Known Activations