© 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. 29703
    Prev
    Next
    INDEX
    Explanations

    occurrences of the character '`' and the specific phrase "in an" at the end of sentences

    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
    23
    +0.21
    1.2%
    258
    +0.20
    1.2%
    478
    +0.19
    1.1%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    258
    +0.21
    0.01
    307
    +0.20
    0.01
    220
    +0.19
    0.01
    Negative Logits
    ahan
    -1.81
    iat
    -1.74
    nikov
    -1.73
    film
    -1.72
    esy
    -1.70
    cad
    -1.63
    ]];
    -1.60
    inski
    -1.59
    oj
    -1.58
    ius
    -1.58
    POSITIVE LOGITS
    ĥ½
    2.69
    Ķ
    2.62
    Ī
    2.52
    ĻĤ
    2.49
    Ĵ
    2.48
    Į
    2.47
    į
    2.33
    Ŀ
    2.03
    ľ
    2.03
    ĨĴ
    2.01
    Activations Density 0.025%

    No Known Activations