© 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. 1-RES-JB
    11. 24229
    Prev
    Next
    INDEX
    Explanations

    phrases related to sacrifice or negative consequences

    oai_token-act-pair · gpt-3.5-turbo

    discussions about the concept of expense, particularly when it impacts others negatively

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odes
    -0.91
     Aval
    -0.86
    rams
    -0.74
     Breaking
    -0.68
    estone
    -0.67
    nai
    -0.66
    Reviewed
    -0.64
    jong
    -0.63
    âĢ¢âĢ¢
    -0.62
    smoking
    -0.62
    POSITIVE LOGITS
     expense
    1.22
    itures
    1.04
     expenses
    0.87
     incurred
    0.85
    folios
    0.84
     reimburse
    0.81
    iture
    0.78
     expenditure
    0.78
    xual
    0.77
    atre
    0.74
    Activations Density 0.004%

    No Known Activations