© 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. 11-RES-JB
    11. 4752
    Prev
    Next
    INDEX
    Explanations

    phrases implying a continuous increase in intensity or activity

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a trend of increasing behaviors or emotions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.75
    hra
    -0.73
    glers
    -0.72
    pring
    -0.70
    oops
    -0.70
     Whip
    -0.70
    iversary
    -0.68
    ENA
    -0.68
    rats
    -0.67
    pta
    -0.66
    POSITIVE LOGITS
     sophisticated
    1.00
     reliant
    0.98
     frustrated
    0.96
     prevalent
    0.93
     polarized
    0.89
     agitated
    0.88
     erratic
    0.88
     desperate
    0.88
     adept
    0.87
     embold
    0.86
    Activations Density 0.070%

    No Known Activations