© 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. 6827
    Prev
    Next
    INDEX
    Explanations

    terms related to academic subjects such as biology, anatomy, psychology, economics, and physiology

    oai_token-act-pair · gpt-3.5-turbo

    topics related to biology, anatomy, and psychology

    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
    ishers
    -0.68
    fman
    -0.68
    fires
    -0.68
    holders
    -0.66
    ership
    -0.65
    leased
    -0.65
    etime
    -0.64
    estead
    -0.63
    izen
    -0.62
    eless
    -0.62
    POSITIVE LOGITS
     textbooks
    1.12
     professor
    1.01
    utics
    0.97
     textbook
    0.90
    istry
    0.88
    ology
    0.86
    icist
    0.85
     lecturer
    0.85
     professors
    0.84
    ologies
    0.83
    Activations Density 0.138%

    No Known Activations