© 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. 27899
    Prev
    Next
    INDEX
    Explanations

    file paths or directory 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
    410
    +0.15
    0.8%
    53
    +0.13
    0.7%
    507
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    214
    +0.15
    0.01
    114
    +0.13
    0.01
    248
    +0.13
    0.01
    Negative Logits
    ERY
    -1.70
    ETHOD
    -1.68
    unch
    -1.59
    availability
    -1.56
    uckland
    -1.55
    \#
    -1.51
    CRO
    -1.49
    Docket
    -1.48
    atin
    -1.48
    arnings
    -1.47
    POSITIVE LOGITS
    ¿½
    3.88
    ĥ
    3.58
    ¾
    3.58
    Į
    3.44
    ĻĤ
    3.42
    Ģ
    3.39
    Ĭ
    3.32
    ģ
    3.31
    º
    3.25
    IJ
    3.25
    Activations Density 0.010%

    No Known Activations