© 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. 23120
    Prev
    Next
    INDEX
    Explanations

    phrases related to observation and comparison, particularly focusing on locations and visual elements

    oai_token-act-pair · gpt-3.5-turbo

    conjunctions and phrases that express accumulation or multiple items

    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
    ãĤ´ãĥ³
    -1.00
     ®
    -0.71
     Released
    -0.65
    hered
    -0.63
    éŃĶ
    -0.61
    amous
    -0.61
    rupted
    -0.60
    successfully
    -0.60
    ulent
    -0.60
    NULL
    -0.60
    POSITIVE LOGITS
     stuff
    1.32
     everybody
    1.25
     we
    1.12
     I
    1.11
     blah
    1.10
     yeah
    1.08
     somebody
    1.06
     then
    1.05
     everything
    1.04
     hopefully
    1.03
    Activations Density 0.254%

    No Known Activations