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. 27323
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this."

    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
    93
    +0.13
    0.7%
    99
    +0.12
    0.7%
    86
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.13
    0.16
    26
    +0.12
    0.14
    199
    +0.10
    0.14
    Negative Logits
    ¿½
    -3.45
    Ĥ¬
    -3.27
    ĥ½
    -3.18
    Ļª
    -3.13
    Į
    -3.13
    ķ
    -3.07
    ĨĴ
    -3.05
    Ĭ
    -3.05
    ĺ
    -2.98
    §
    -2.97
    POSITIVE LOGITS
    \].
    1.66
     ](
    1.59
    ilic
    1.52
    RSOS
    1.51
    imeters
    1.50
     ([*
    1.48
    arrant
    1.48
    .](
    1.40
    Availability
    1.38
    ress
    1.36
    Activations Density 0.358%

    No Known Activations