© 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. 20410
    Prev
    Next
    INDEX
    Explanations

    qualities related to physical attributes such as texture, look, size, quality, speed, and agility

    oai_token-act-pair · gpt-3.5-turbo

    characteristics and attributes of objects or subjects

    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
    >>>>
    -0.69
    answer
    -0.65
     EVENTS
    -0.61
    inately
    -0.60
    isible
    -0.60
    inite
    -0.59
     WEEK
    -0.58
    ongo
    -0.58
     istg
    -0.57
    ividual
    -0.57
    POSITIVE LOGITS
     pioneered
    1.02
     of
    0.97
     seen
    0.91
     typical
    0.91
     described
    0.86
     favoured
    0.85
     favored
    0.85
     envisioned
    0.84
     afforded
    0.84
     outlined
    0.81
    Activations Density 0.199%

    No Known Activations