© 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. 29852
    Prev
    Next
    INDEX
    Explanations

    significant numerical values or constants in data

    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
    242
    +0.15
    0.8%
    205
    +0.13
    0.7%
    376
    +0.13
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.15
    0.12
    209
    +0.13
    0.10
    495
    +0.13
    0.08
    Negative Logits
    ĺ
    -2.75
    ¶
    -2.60
    ·
    -2.49
    ĥ½
    -2.43
    ¡
    -2.38
    µ
    -2.37
    Ħ
    -2.36
    ±
    -2.29
    Į
    -2.25
    Ŀ
    -2.23
    POSITIVE LOGITS
    :=
    1.71
    ename
    1.66
    osto
    1.53
     affirm
    1.45
     Institute
    1.44
    ety
    1.43
    isme
    1.43
    enÃŃ
    1.42
    ientos
    1.41
    ÅĽÄĩ
    1.40
    Activations Density 0.177%

    No Known Activations