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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 27675
    Prev
    Next
    INDEX
    Explanations

    repeated references to "it" and "this," indicating a focus on items or subjects being emphasized in the text

    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
    118
    +0.14
    0.8%
    124
    +0.13
    0.7%
    358
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    352
    +0.14
    0.20
    185
    +0.13
    0.17
    154
    +0.12
    0.17
    Negative Logits
    ¦
    -1.69
    ¨
    -1.63
     throat
    -1.56
     eyes
    -1.52
    ĺ
    -1.51
    Į
    -1.49
    â̝
    -1.47
    ¬
    -1.41
    pective
    -1.38
    (*
    -1.38
    POSITIVE LOGITS
    cé
    2.06
    lemental
    1.98
    ld
    1.64
    gos
    1.57
    onaut
    1.53
    abling
    1.50
    zheimer
    1.49
    zing
    1.46
    lex
    1.44
    doi
    1.44
    Activations Density 0.840%

    No Known Activations