© 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. 2-RES-JB
    11. 4432
    Prev
    Next
    INDEX
    Explanations

    names or words related to the name "Kroll"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "roll" and its variants

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    natureconservancy
    -0.72
     Ib
    -0.63
     Realms
    -0.62
     Fas
    -0.61
     unin
    -0.57
     Holo
    -0.57
    cond
    -0.57
    ¿½
    -0.56
     Cedar
    -0.56
     Liber
    -0.56
    POSITIVE LOGITS
    roll
    1.14
    rolling
    0.94
    sheet
    0.87
    owship
    0.86
    outing
    0.85
    crow
    0.84
    ength
    0.82
    ies
    0.80
    ows
    0.79
    back
    0.78
    Activations Density 0.004%

    No Known Activations