© 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. 8-RES-JB
    11. 2406
    Prev
    Next
    INDEX
    Explanations

    the acronym "BI" with different levels of emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to Building Information Modeling (BIM)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lain
    -0.92
    isting
    -0.72
    earchers
    -0.68
    ength
    -0.67
    izational
    -0.65
    ional
    -0.64
    entially
    -0.61
    izing
    -0.60
    rooms
    -0.60
    ting
    -0.60
    POSITIVE LOGITS
    undo
    0.94
    ased
    0.88
    ases
    0.85
    ASED
    0.85
    otech
    0.81
    TeX
    0.81
    ļéĨĴ
    0.80
    ī
    0.79
    omial
    0.76
    ĸļ
    0.76
    Activations Density 0.032%

    No Known Activations