© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 19365
    Prev
    Next
    INDEX
    Explanations

    government-related entities and mentions of physical locations

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to records, data, and statistics

    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
     guiName
    -0.55
     Solitaire
    -0.49
     guiActiveUnfocused
    -0.48
     ;)
    -0.47
     pioneered
    -0.46
     arrives
    -0.46
     CrossRef
    -0.46
     handshake
    -0.45
     (?,
    -0.45
     Murdoch
    -0.44
    POSITIVE LOGITS
    »
    0.76
    ī
    0.70
    º
    0.67
    ·
    0.65
    ãĥ³
    0.64
    ®
    0.64
    ¸
    0.64
    ãĥİ
    0.61
    ©
    0.60
    ħ
    0.60
    Activations Density 1.178%

    No Known Activations