© 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
    2. Under Peer Review · Sparse Autoencoders for Pythia-70M-Deduped
    3. Pythia-70M-Deduped
    4. MLP Post
    5. 0-MLP-SM
    6. 27771
    Prev
    Next
    INDEX
    Explanations

    expressions of satisfaction or dissatisfaction

    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
    +0.18
    1.0%
    380
    +0.13
    0.7%
    9
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    9
    +0.18
    0.02
    105
    +0.13
    0.01
    380
    +0.11
    0.01
    Negative Logits
    OE
    -1.77
    EP
    -1.48
    aged
    -1.40
    HN
    -1.38
    Pacific
    -1.36
    Ïģγ
    -1.36
    YE
    -1.34
    rise
    -1.34
    hire
    -1.30
    itti
    -1.27
    POSITIVE LOGITS
     ones
    2.01
    ely
    2.00
    edly
    1.72
    ivable
    1.59
    otal
    1.57
    bourg
    1.53
    eville
    1.47
    tons
    1.44
    iculously
    1.44
    arius
    1.38
    Activations Density 0.011%

    No Known Activations