© 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. 11-RES-JB
    11. 23226
    Prev
    Next
    INDEX
    Explanations

    dates and historical events

    oai_token-act-pair · gpt-3.5-turbo

    forms of the verb "to be" in past tense

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inas
    -0.65
     Saying
    -0.64
    ettle
    -0.63
     Needs
    -0.63
    iliar
    -0.62
     Checking
    -0.62
     IMAGES
    -0.62
     Lines
    -0.61
     Costs
    -0.60
     Conditions
    -0.60
    POSITIVE LOGITS
     subsequently
    1.44
     eventually
    1.37
     later
    1.25
     renamed
    1.22
     promptly
    1.14
     thereafter
    1.10
     ultimately
    1.07
     instrumental
    1.07
     then
    1.05
     scrapped
    1.03
    Activations Density 0.285%

    No Known Activations