© 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. 9-RES-JB
    11. 7557
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific types of skills, tools, or activities

    oai_token-act-pair · gpt-3.5-turbo

    specific terms related to various systems and classifications

    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
    )=(
    -0.62
    ertodd
    -0.58
    utics
    -0.56
     beware
    -0.53
     âĵĺ
    -0.52
    hots
    -0.51
    terday
    -0.50
    govtrack
    -0.50
    fetched
    -0.48
     wat
    -0.47
    POSITIVE LOGITS
    osphere
    0.82
     portion
    0.79
    iest
    0.76
     continuum
    0.71
     aspect
    0.71
    icter
    0.70
    liest
    0.67
     section
    0.66
     version
    0.65
     element
    0.65
    Activations Density 1.003%

    No Known Activations