© 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. 18602
    Prev
    Next
    INDEX
    Explanations

    adjectives related to textures

    oai_token-act-pair · gpt-3.5-turbo

    adjectives ending in the letter 'y'

    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
    OTO
    -0.76
    rican
    -0.76
    igate
    -0.76
    Ī
    -0.73
    osponsors
    -0.69
    Course
    -0.69
    uther
    -0.68
    SEA
    -0.68
    OTOS
    -0.67
    significant
    -0.67
    POSITIVE LOGITS
     grin
    0.94
     conco
    0.86
     affair
    0.84
    ness
    0.84
     tones
    0.83
     beginnings
    0.82
     goodness
    0.81
     underside
    0.81
     eyed
    0.79
     slopes
    0.79
    Activations Density 0.200%

    No Known Activations