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. 27762
    Prev
    Next
    INDEX
    Explanations

    the term "Standard" in various contexts related to specifications or quality measures

    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
    268
    +0.13
    0.7%
    380
    +0.13
    0.7%
    246
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    89
    +0.13
    0.02
    268
    +0.13
    0.01
    380
    +0.12
    0.01
    Negative Logits
    ¬
    -1.88
    ·¸
    -1.84
    ĥ½
    -1.79
    \)
    -1.61
    ths
    -1.57
    henyl
    -1.56
    Ģ
    -1.55
    Ĥ
    -1.54
    ¿½
    -1.52
    ĥ
    -1.46
    POSITIVE LOGITS
    TV
    1.72
    bank
    1.68
    procedure
    1.67
    lite
    1.62
    ipore
    1.62
    ium
    1.50
    boro
    1.50
    made
    1.48
    ço
    1.45
    ista
    1.44
    Activations Density 0.012%

    No Known Activations