© 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. 7-RES-JB
    11. 23378
    Prev
    Next
    INDEX
    Explanations

    comparatives and superlatives related to quantity or degree, such as "higher", "lower", "soaring", "plummeting", and "declining"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to economic changes and market conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fuck
    -0.89
    mere
    -0.77
    hal
    -0.76
    ayer
    -0.75
    ittee
    -0.75
    Haunted
    -0.73
    yes
    -0.71
    break
    -0.71
    ieu
    -0.71
    ittees
    -0.71
    POSITIVE LOGITS
     performance
    1.11
     rates
    1.05
     productivity
    1.01
     susceptibility
    0.99
     intakes
    0.98
     expectations
    0.98
     wages
    0.97
     mobility
    0.96
     enrollment
    0.96
     incomes
    0.96
    Activations Density 0.266%

    No Known Activations