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. 27375
    Prev
    Next
    INDEX
    Explanations

    words ending with the suffix "ically"

    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
    376
    +0.17
    1.0%
    108
    +0.12
    0.7%
    2
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    379
    +0.17
    0.02
    19
    +0.12
    0.02
    438
    +0.12
    0.02
    Negative Logits
    ·¸
    -3.42
    ħ
    -3.33
    Ĭ
    -3.23
    Ķ
    -3.09
    ½
    -3.07
    »¿
    -3.05
    ®
    -3.02
    Ī
    -3.00
    »
    -2.96
    Ĥ¬
    -2.95
    POSITIVE LOGITS
    ball
    1.47
     league
    1.44
     speaking
    1.42
    fecture
    1.41
    shock
    1.40
    looking
    1.37
     Speaking
    1.32
    ribution
    1.31
    geon
    1.30
    mph
    1.30
    Activations Density 4.885%

    No Known Activations