© 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. 0-MLP-SM
    11. 27154
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns referring to collective ownership

    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
    17
    +0.14
    0.8%
    279
    +0.12
    0.7%
    9
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    402
    +0.14
    0.13
    338
    +0.12
    0.12
    240
    +0.11
    0.11
    Negative Logits
     backdrop
    -1.71
    ¯
    -1.65
     spread
    -1.45
     persisted
    -1.42
     escal
    -1.41
    ially
    -1.40
    uct
    -1.39
    à±ģ
    -1.35
     continued
    -1.33
    à¯ģ
    -1.32
    POSITIVE LOGITS
    ums
    1.40
    umni
    1.34
     minors
    1.33
     AFL
    1.32
    ighb
    1.31
    ige
    1.28
     collectors
    1.24
    oses
    1.24
     Problems
    1.23
    irds
    1.23
    Activations Density 0.299%

    No Known Activations