© 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. 2-MLP-SM
    6. 26433
    Prev
    Next
    INDEX
    Explanations

    terms related to large quantities or sizes

    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
    431
    +0.10
    0.6%
    72
    +0.10
    0.6%
    150
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    193
    +0.10
    0.05
    248
    +0.10
    0.05
    118
    +0.10
    0.08
    Negative Logits
    ³
    -2.82
    »¿
    -2.74
    ·
    -2.74
    Ļª
    -2.68
    °
    -2.68
    Ħ
    -2.47
    »
    -2.44
    ĺ
    -2.42
    ĩ
    -2.42
    ·¸
    -2.40
    POSITIVE LOGITS
    amais
    1.53
    óg
    1.53
    ÃŃst
    1.52
     itiner
    1.52
    oxford
    1.44
    **:
    1.44
    **^
    1.40
     biography
    1.33
    orth
    1.33
    ERTYPE
    1.30
    Activations Density 1.181%

    No Known Activations