© 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. 27927
    Prev
    Next
    INDEX
    Explanations

    instances of specific numerical values or codes

    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
    +0.14
    0.8%
    274
    +0.13
    0.7%
    111
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    203
    +0.14
    0.01
    214
    +0.13
    0.01
    274
    +0.12
    0.01
    Negative Logits
     */
    -1.64
     knees
    -1.53
     };
    -1.51
    hip
    -1.47
    @{
    -1.44
     ];
    -1.44
    hips
    -1.42
    hey
    -1.38
     matter
    -1.37
    .";
    -1.37
    POSITIVE LOGITS
    ª
    2.25
    ¯
    2.21
    ¤
    2.18
    ³
    2.09
    °
    2.08
    ¹
    2.08
    ı
    2.08
    ĨĴ
    2.08
    ļ
    2.06
    ¨
    1.98
    Activations Density 3.064%

    No Known Activations