© 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. 27183
    Prev
    Next
    INDEX
    Explanations

    specific numerical values or identifiers, particularly those related to sections or references in formal documents

    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
    458
    +0.15
    0.8%
    467
    +0.14
    0.8%
    81
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    458
    +0.15
    0.03
    436
    +0.14
    0.02
    262
    +0.14
    0.02
    Negative Logits
    rape
    -1.63
    river
    -1.49
     pity
    -1.48
    opo
    -1.46
     responsibility
    -1.43
    ocol
    -1.41
    AAAAAAAA
    -1.40
     vain
    -1.40
    etica
    -1.34
    ward
    -1.34
    POSITIVE LOGITS
    ®
    1.68
    ³
    1.60
    Ľ
    1.59
    ¶
    1.57
    Ĭ
    1.52
    inski
    1.46
     ($(
    1.45
     matches
    1.44
    µ
    1.40
    bital
    1.39
    Activations Density 1.384%

    No Known Activations