© 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. 2-MLP-SM
    11. 26601
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to machine learning and its applications in various contexts

    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/2-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.2.hook_mlp_out
    Hook Layer
    2
    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
    290
    +0.12
    0.7%
    325
    +0.12
    0.7%
    259
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    243
    +0.12
    0.13
    335
    +0.12
    0.11
    325
    +0.12
    0.08
    Negative Logits
    psis
    -1.55
     both
    -1.44
    pone
    -1.43
    pless
    -1.42
    ively
    -1.39
    nier
    -1.35
     each
    -1.34
    aves
    -1.34
     careers
    -1.33
    iday
    -1.28
    POSITIVE LOGITS
    ¯
    2.60
    ¢
    2.48
    Ļª
    2.41
    ¬
    2.36
    Ļ
    2.31
    ¶
    2.30
    µ
    2.22
    Ĺ
    2.21
    ļ
    2.20
    ij
    2.17
    Activations Density 3.122%

    No Known Activations