© 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. 4-RES-JB
    11. 20838
    Prev
    Next
    INDEX
    Explanations

    indications related to legal documents and arguments

    oai_token-act-pair · gpt-3.5-turbo

    instances of a specific symbol or character encoding in the text

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

    No Comments

    Negative Logits
     dumps
    -0.78
     favourite
    -0.78
     congratulations
    -0.75
    ctors
    -0.75
    onut
    -0.72
    anish
    -0.70
     condol
    -0.70
     mosqu
    -0.69
     banana
    -0.69
     watches
    -0.67
    POSITIVE LOGITS
    Footnote
    1.07
    âĢł
    1.02
    ¶
    1.00
    §
    0.99
    ĸļ
    0.92
    Demand
    0.90
    catentry
    0.90
    bryce
    0.89
    º
    0.89
    âĨij
    0.87
    Activations Density 0.525%

    No Known Activations