© 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. 29240
    Prev
    Next
    INDEX
    Explanations

    structured data and graphical representations within a programming context

    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
    452
    +0.15
    0.9%
    271
    +0.12
    0.7%
    440
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    438
    +0.15
    0.40
    53
    +0.12
    0.42
    56
    +0.12
    0.11
    Negative Logits
    lessness
    -1.57
    leading
    -1.53
    lessly
    -1.53
    factor
    -1.47
    fiddle
    -1.42
    asmod
    -1.40
     adolescence
    -1.35
     puzzle
    -1.35
    oning
    -1.33
    bent
    -1.33
    POSITIVE LOGITS
    ĻĤ
    6.34
    «
    5.59
    Ļ
    5.52
    ·
    5.42
    ½
    5.24
    ħ
    5.21
    ©
    5.20
    ¿
    5.16
    ľĵ
    5.13
    ¢
    5.13
    Activations Density 4.698%

    No Known Activations