© 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. 9-RES-JB
    11. 5063
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the term "Bro"

    oai_token-act-pair · gpt-3.5-turbo

    repetitions of the word "Bro."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aneous
    -0.66
    urers
    -0.65
     repetition
    -0.65
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.64
    ory
    -0.64
     Dull
    -0.62
    uate
    -0.62
    ARY
    -0.61
    EMP
    -0.61
    uality
    -0.59
    POSITIVE LOGITS
    ccoli
    1.32
    oks
    1.24
    thel
    1.22
    dy
    1.07
    oke
    1.05
    swer
    1.03
    kens
    0.97
    chet
    0.94
    gue
    0.92
    idered
    0.92
    Activations Density 0.025%

    No Known Activations