© 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. 2-MLP-SM
    11. 23037
    Prev
    Next
    INDEX
    Explanations

    affirmative responses or agreement in communication

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    5
    +0.14
    0.8%
    95
    +0.13
    0.7%
    179
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    5
    +0.14
    0.03
    82
    +0.13
    0.02
    95
    +0.12
    0.03
    Negative Logits
    ĻĤ
    -2.92
    ²
    -2.71
    ´
    -2.69
    ĸ´
    -2.65
    Ļª
    -2.63
    ·¸
    -2.52
    Ķ
    -2.42
    Į
    -2.37
    ↵
    -2.37
    ↵↵
    -2.37
    POSITIVE LOGITS
    ftware
    1.46
     android
    1.43
     required
    1.40
     whilst
    1.36
     platform
    1.35
     Parliament
    1.33
     acting
    1.32
    verts
    1.32
     invalid
    1.29
     parliament
    1.29
    Activations Density 0.167%

    No Known Activations