© 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. 6365
    Prev
    Next
    INDEX
    Explanations

    words related to sliminess

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "slug."

    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
    ICLE
    -0.96
     Continued
    -0.74
    enegger
    -0.73
    IFIC
    -0.71
    ãģ®éŃĶ
    -0.67
     EVENT
    -0.67
     Cause
    -0.67
     Sense
    -0.66
    heid
    -0.66
     doi
    -0.65
    POSITIVE LOGITS
    ither
    1.03
    asher
    1.03
    udge
    1.02
    anted
    1.00
    ashes
    0.98
    inking
    0.98
    anders
    0.96
    ashed
    0.95
    anguage
    0.94
    ittle
    0.92
    Activations Density 0.007%

    No Known Activations