© 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. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 1061
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Lamborghini."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Lam" and related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Subtle
    -0.98
     Marketable
    -0.80
    ãģį
    -0.74
     Occupations
    -0.74
    ģĸ
    -0.71
    IBLE
    -0.68
     Fiction
    -0.67
    dit
    -0.63
    055
    -0.63
    FUL
    -0.62
    POSITIVE LOGITS
    borgh
    1.49
     Lam
    1.00
    ont
    0.99
    amo
    0.97
    pton
    0.87
    inated
    0.87
    onte
    0.87
    mer
    0.86
    oran
    0.85
    ouse
    0.84
    Activations Density 0.005%

    No Known Activations