Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 17479
    Prev
    Next
    INDEX
    Explanations

    phrases related to descriptions, explanations, or observations

    oai_token-act-pair · gpt-3.5-turbo

    statements and assertions about current conditions or observations

    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
    eor
    -0.72
    agues
    -0.69
    ievers
    -0.69
    iard
    -0.64
     ceremon
    -0.64
    aints
    -0.62
     whis
    -0.61
     helm
    -0.60
    luaj
    -0.59
    aine
    -0.58
    POSITIVE LOGITS
    olation
    0.78
     Madness
    0.76
     extraordinary
    0.75
     nothing
    0.75
     astounding
    0.73
    olated
    0.72
     something
    0.71
    Reviewer
    0.71
    KER
    0.70
     unbelievable
    0.70
    Activations Density 0.121%

    No Known Activations