© 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. 8-RES-JB
    11. 20330
    Prev
    Next
    INDEX
    Explanations

    proper nouns, potentially related to politics and world events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "the" in various contexts

    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
    Ò
    -0.83
    SPONSORED
    -0.77
    antes
    -0.76
    nit
    -0.74
    atown
    -0.74
    ceive
    -0.73
    etsy
    -0.73
    !!!!
    -0.73
    fg
    -0.72
    ea
    -0.71
    POSITIVE LOGITS
     latest
    1.21
     latter
    1.15
     remainder
    1.02
     Associated
    1.01
     stakes
    0.97
     agency
    0.96
     deadline
    0.96
     announcement
    0.94
    oret
    0.94
     biggest
    0.94
    Activations Density 0.498%

    No Known Activations