© 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. 28052
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "port" 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
    43
    +0.11
    0.6%
    217
    +0.11
    0.6%
    189
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    449
    +0.11
    0.02
    43
    +0.11
    0.02
    220
    +0.10
    0.02
    Negative Logits
    ´
    -2.20
    ¿
    -2.20
    Ĥ¬
    -2.00
    ·¸
    -1.98
    Ļª
    -1.89
    ĺ
    -1.89
    ³
    -1.88
    µ
    -1.88
    §
    -1.87
    ¶
    -1.86
    POSITIVE LOGITS
    folio
    2.61
    raits
    2.06
    ious
    1.92
    ions
    1.90
    boro
    1.86
    arium
    1.85
    ivist
    1.79
    ’
    1.77
    ional
    1.74
    IVE
    1.71
    Activations Density 0.015%

    No Known Activations