© 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. 8-RES-JB
    11. 2475
    Prev
    Next
    INDEX
    Explanations

    phrases related to body parts and actions

    oai_token-act-pair · gpt-3.5-turbo

    possessive pronouns and references to ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hereafter
    -0.73
     Rowling
    -0.73
     Pwr
    -0.67
    GAN
    -0.66
    '-
    -0.65
     Eucl
    -0.64
     Hear
    -0.64
     Izan
    -0.62
    ablishment
    -0.62
     Aren
    -0.61
    POSITIVE LOGITS
     own
    1.38
     fingers
    1.05
     knees
    1.01
    selves
    1.00
     nose
    0.98
     fists
    0.96
    self
    0.96
     toes
    0.94
     hips
    0.93
     lips
    0.91
    Activations Density 0.146%

    No Known Activations