© 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. 30649
    Prev
    Next
    INDEX
    Explanations

    references to competitive situations or actions

    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
    283
    +0.14
    0.8%
    221
    +0.11
    0.6%
    339
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    283
    +0.14
    0.02
    481
    +0.11
    0.02
    263
    +0.11
    0.01
    Negative Logits
    unnumbered
    -2.08
     recent
    -1.64
     Respondents
    -1.51
     unders
    -1.45
     .=
    -1.44
    ../../
    -1.44
    rapeutics
    -1.42
    ____________
    -1.41
    Appellee
    -1.40
    icrobial
    -1.39
    POSITIVE LOGITS
    able
    1.74
    encial
    1.67
    heit
    1.65
    ings
    1.65
    án
    1.64
    ably
    1.60
    hoc
    1.59
     positions
    1.57
    ingly
    1.57
     defenses
    1.56
    Activations Density 0.012%

    No Known Activations