© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    5. Pythia-70M-Deduped
    7. MLP Post
    9. 2-MLP-SM
    11. 26074
    Prev
    Next
    INDEX
    Explanations

    terms related to counting or numeric values

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    156
    +0.13
    0.7%
    55
    +0.12
    0.7%
    197
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.13
    0.03
    10
    +0.12
    0.06
    50
    +0.11
    0.03
    Negative Logits
    documentclass
    -1.60
    áĢ¯
    -1.48
    ogra
    -1.44
    Errno
    -1.43
    ested
    -1.42
    áĢ¬
    -1.39
    à°¿
    -1.39
    à±ģ
    -1.35
    ()</
    -1.33
    specified
    -1.30
    POSITIVE LOGITS
    ¿
    3.73
    µ
    3.59
    Ģ
    3.54
    ĵ
    3.47
    ³
    3.46
    ¤
    3.42
    ħ
    3.37
    ¦
    3.34
    ¾
    3.33
    ĥ
    3.33
    Activations Density 1.360%

    No Known Activations