© 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. 30852
    Prev
    Next
    INDEX
    Explanations

    error messages indicating issues or exceptions in code

    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
    376
    +0.21
    1.2%
    365
    +0.11
    0.6%
    467
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    341
    +0.21
    0.01
    392
    +0.11
    0.01
    114
    +0.10
    0.01
    Negative Logits
    ]>
    -1.77
    |}
    -1.62
     Your
    -1.59
    ]}
    -1.55
    \}}
    -1.50
     your
    -1.50
     called
    -1.47
    )$)
    -1.43
     waters
    -1.41
     sweat
    -1.40
    POSITIVE LOGITS
    ĻĤ
    2.33
    ª
    2.11
    £
    2.09
    Į
    1.95
    hole
    1.93
    ¾
    1.92
    ¡
    1.89
    ®
    1.83
    ²
    1.82
    holes
    1.80
    Activations Density 0.017%

    No Known Activations