© 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. 27894
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the concept of 'guidance' or 'direction'

    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
    83
    +0.13
    0.7%
    275
    +0.13
    0.7%
    92
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    117
    +0.13
    0.07
    107
    +0.13
    0.06
    95
    +0.12
    0.06
    Negative Logits
    maker
    -1.75
    hl
    -1.64
    ÅĪ
    -1.63
     ruler
    -1.58
    thouse
    -1.50
    ^[@
    -1.50
    chte
    -1.50
    ière
    -1.45
    ichte
    -1.44
    kte
    -1.43
    POSITIVE LOGITS
    Ĭ
    2.25
    ·
    2.23
    ¶
    2.21
    ľĵ
    2.11
    Ĺ
    1.99
    Ń
    1.96
    º
    1.84
    ī
    1.83
    ľ
    1.81
    Ŀ
    1.78
    Activations Density 0.048%

    No Known Activations