© 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. 16182
    Prev
    Next
    INDEX
    Explanations

    phrases related to methods, processes, or instructions

    oai_token-act-pair · gpt-3.5-turbo

    repetitive conjunctions and phrases related to questioning circumstances or conditions

    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
    IRE
    -0.67
     Roller
    -0.63
     Gry
    -0.62
     Kirin
    -0.59
     Mens
    -0.59
     Sixth
    -0.58
     Swan
    -0.57
     Pyramid
    -0.56
     Yog
    -0.56
    Wan
    -0.56
    POSITIVE LOGITS
    why
    1.04
    rogens
    1.02
    rogen
    0.94
    abouts
    0.93
     WHY
    0.87
    anwhile
    0.84
     whence
    0.83
    tymology
    0.82
     why
    0.80
     exactly
    0.78
    Activations Density 0.067%

    No Known Activations