© 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. 18567
    Prev
    Next
    INDEX
    Explanations

    questions that are frequently asked or common in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate frequently asked questions

    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
    ibur
    -0.68
     dispers
    -0.62
     sealing
    -0.61
     cooperating
    -0.61
    imately
    -0.59
     Integrity
    -0.58
     Extrem
    -0.58
    etting
    -0.57
     Sever
    -0.57
     Bet
    -0.57
    POSITIVE LOGITS
     misconceptions
    0.97
     wondering
    0.97
     mistakenly
    0.94
     errone
    0.88
    Quote
    0.87
     misconception
    0.86
     wondered
    0.85
    ItemImage
    0.83
    Myth
    0.82
     anecd
    0.82
    Activations Density 0.447%

    No Known Activations