© 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. 4550
    Prev
    Next
    INDEX
    Explanations

    terms related to different industries or fields such as healthcare, aviation, culinary, weather, energy, automotive, and more

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health, aviation, and food

    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
    lain
    -0.73
     AFB
    -0.68
    /.
    -0.67
    raviolet
    -0.67
    ||||
    -0.67
    DAQ
    -0.64
     Gund
    -0.64
     Naval
    -0.63
    OY
    -0.63
     Peters
    -0.62
    POSITIVE LOGITS
     historian
    0.79
     historians
    0.76
    week
    0.74
    speak
    0.68
     philos
    0.67
    odynam
    0.67
    books
    0.66
    service
    0.65
    technology
    0.64
    space
    0.62
    Activations Density 0.673%

    No Known Activations