© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1917
    Prev
    Next
    INDEX
    Explanations

    phrases related to capturing or obtaining something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "catch."

    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
    ©¶æ
    -0.83
     prevailing
    -0.77
     aggrav
    -0.76
     accelerated
    -0.76
     exha
    -0.76
     occas
    -0.74
    ccording
    -0.70
     fracturing
    -0.69
     pronoun
    -0.69
     embr
    -0.68
    POSITIVE LOGITS
    atch
    1.33
    atches
    1.17
    atching
    1.16
    ATCH
    1.00
    aways
    0.98
    athon
    0.89
    oons
    0.86
    atched
    0.83
    ings
    0.81
    bowl
    0.78
    Activations Density 0.007%

    No Known Activations