© 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. 26437
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'Inter' 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
    59
    +0.15
    0.8%
    287
    +0.13
    0.7%
    483
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    287
    +0.15
    0.03
    483
    +0.13
    0.03
    112
    +0.13
    0.03
    Negative Logits
    elta
    -1.74
    ureus
    -1.71
    elt
    -1.57
     below
    -1.54
    ets
    -1.49
    emic
    -1.43
    ukes
    -1.37
    ocardi
    -1.37
    erate
    -1.36
    ert
    -1.35
    POSITIVE LOGITS
    stitial
    1.58
    goog
    1.40
    hair
    1.39
    face
    1.33
    mediate
    1.31
    hua
    1.31
    judicial
    1.31
    done
    1.30
    strand
    1.29
    ior
    1.26
    Activations Density 0.023%

    No Known Activations