Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27649
    Prev
    Next
    INDEX
    Explanations

    instances of copyright notices

    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
    261
    +0.13
    0.7%
    398
    +0.10
    0.6%
    121
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    261
    +0.13
    0.04
    398
    +0.10
    0.04
    121
    +0.10
    0.03
    Negative Logits
    Ł
    -2.01
    ·
    -1.92
    »
    -1.80
    µ
    -1.80
    ¸
    -1.74
    ¶
    -1.73
    ³
    -1.65
    ´
    -1.63
    ·¸
    -1.62
    ĨĴ
    -1.62
    POSITIVE LOGITS
    ités
    1.76
    urities
    1.75
    ément
    1.74
    krit
    1.72
    uscript
    1.70
    ptions
    1.66
    ariable
    1.66
    ceptible
    1.65
    genstein
    1.65
    icul
    1.62
    Activations Density 0.082%

    No Known Activations