© 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. 15127
    Prev
    Next
    INDEX
    Explanations

    websites with URLs

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of web addresses or URLs

    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
     expulsion
    -0.74
     recess
    -0.67
     succeeding
    -0.64
     sway
    -0.63
     conformity
    -0.63
     expel
    -0.62
     surn
    -0.61
     proportion
    -0.61
     Labrador
    -0.61
     Vaj
    -0.61
    POSITIVE LOGITS
    www
    1.20
    ://
    1.06
    forum
    1.01
    natureconservancy
    1.01
    ww
    0.93
    forums
    0.92
     www
    0.89
    ctl
    0.88
    youtu
    0.87
    pages
    0.85
    Activations Density 0.013%

    No Known Activations