© 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. 10-RES-JB
    11. 21635
    Prev
    Next
    INDEX
    Explanations

    key adjectives emphasizing significance, importance, and consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    adjectives expressing significance or intensity

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nope
    -0.68
     dunno
    -0.67
     invincible
    -0.64
     bye
    -0.63
     tons
    -0.62
    «ĺ
    -0.62
    Complete
    -0.60
     everything
    -0.60
     bland
    -0.60
     identical
    -0.59
    POSITIVE LOGITS
     considering
    0.92
     because
    0.80
     when
    0.78
    because
    0.73
    irtual
    0.72
    outheast
    0.70
     owing
    0.69
     given
    0.69
    ebted
    0.67
     since
    0.66
    Activations Density 0.201%

    No Known Activations