© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 30308
    Prev
    Next
    INDEX
    Explanations

    words that include the suffix 'ize'

    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
    +0.23
    1.3%
    115
    +0.13
    0.7%
    276
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    276
    +0.23
    0.03
    411
    +0.13
    0.02
    504
    +0.12
    0.02
    Negative Logits
    })}
    -1.68
    .");
    -1.60
    *=
    -1.58
    })(
    -1.55
    $]{};
    -1.54
    compan
    -1.52
    called
    -1.52
    \\
    -1.47
    forEach
    -1.46
    })
    -1.46
    POSITIVE LOGITS
    ¬
    2.78
    ķ
    2.77
    ł
    2.76
    °
    2.75
    ĻĤ
    2.73
    ĩ
    2.70
    Ń
    2.66
    č↵         
    2.57
    ↵                            
    2.57
    <|outofrange|>
    2.57
    Activations Density 0.020%

    No Known Activations