© 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 EvalsExportsinterp-engineNEWAPI 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. 29641
    Prev
    Next
    INDEX
    Explanations

    locations and spatial references

    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
    121
    +0.13
    0.7%
    19
    +0.12
    0.7%
    316
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    69
    +0.13
    0.24
    47
    +0.12
    0.16
    173
    +0.12
    0.17
    Negative Logits
    ¸
    -2.63
    Ļª
    -2.56
    ¶
    -2.40
    »¿
    -2.28
    ł
    -2.25
    ↵
    -2.20
    ↵
    -2.20
    -2.20
    č↵
    -2.20
    -2.20
    POSITIVE LOGITS
    ubot
    1.70
    @"
    1.67
    \|^
    1.65
     @
    1.62
    iento
    1.59
    drew
    1.59
    cdots
    1.50
    ubottu
    1.50
    issen
    1.48
    izo
    1.48
    Activations Density 0.696%

    No Known Activations