© 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. 17116
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific industry terms or regulatory compliance

    oai_token-act-pair · gpt-3.5-turbo

    terms related to governmental and corporate structures or institutions

    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
    istically
    -0.74
    aneously
    -0.71
    ning
    -0.70
    liest
    -0.69
    rette
    -0.68
    otos
    -0.68
    less
    -0.67
    onyms
    -0.66
    ously
    -0.66
    ¹
    -0.65
    POSITIVE LOGITS
    mith
    1.62
    ystem
    1.47
    heet
    1.40
    chool
    1.39
    pring
    1.38
    hift
    1.38
    pace
    1.37
    peed
    1.34
    erver
    1.27
    hare
    1.26
    Activations Density 0.449%

    No Known Activations