© 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. 29556
    Prev
    Next
    INDEX
    Explanations

    references to a "receiver" in various contexts

    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
    86
    +0.13
    0.8%
    376
    +0.12
    0.7%
    296
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    86
    +0.13
    0.02
    296
    +0.12
    0.01
    455
    +0.11
    0.01
    Negative Logits
    Ļª
    -1.97
    ĨĴ
    -1.97
    ]>
    -1.86
    ĥ½
    -1.79
    EVER
    -1.75
     yours
    -1.71
     anyone
    -1.66
    reland
    -1.66
    rely
    -1.65
    ĻĤ
    -1.63
    POSITIVE LOGITS
    nement
    1.84
     compartments
    1.83
     belt
    1.80
     (),
    1.77
     (,
    1.76
    ató
    1.75
    ÅĽci
    1.72
     rests
    1.69
    nant
    1.66
     derives
    1.65
    Activations Density 0.019%

    No Known Activations