© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 18687
    Prev
    Next
    INDEX
    Explanations

    phrases that are attributed to someone speaking and often containing direct quotes

    oai_token-act-pair · gpt-3.5-turbo

    quotes or statements made by individuals

    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
     miscarriage
    -0.64
    toggle
    -0.64
    ggles
    -0.63
    Columb
    -0.59
    âĶĢâĶĢâĶĢâĶĢ
    -0.59
    aturday
    -0.59
    Measure
    -0.58
    flush
    -0.58
     Bigfoot
    -0.57
     suites
    -0.57
    POSITIVE LOGITS
     added
    1.38
     emphas
    1.21
     stressed
    1.20
     said
    1.12
     asserted
    1.09
     insisted
    1.08
     emphasized
    1.07
     warned
    1.06
     told
    1.03
     claimed
    1.02
    Activations Density 0.132%

    No Known Activations