© 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. 28737
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or significant figures in data

    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
    458
    +0.18
    1.0%
    81
    +0.14
    0.8%
    69
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.18
    0.08
    58
    +0.14
    0.06
    307
    +0.12
    0.06
    Negative Logits
     pity
    -1.76
    "?"
    -1.69
    hentication
    -1.56
    >$
    -1.44
    '?"
    -1.39
    '?
    -1.39
     herself
    -1.38
     dont
    -1.35
     denial
    -1.32
    AAAAAAAA
    -1.31
    POSITIVE LOGITS
    ³
    2.22
    Ľ
    2.16
    ®
    2.01
    µ
    1.94
    ĥ½
    1.82
    ħ
    1.79
    ļ
    1.78
    ł
    1.77
    ¥
    1.74
    »
    1.72
    Activations Density 0.154%

    No Known Activations