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

    Neuronpedia

    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. 0-RES-JB
    11. 4981
    Prev
    Next
    INDEX
    Explanations

    technical terms or specialized jargon related to camera technology

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific brand or product

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bridgewater
    -0.85
     Clown
    -0.78
    uckland
    -0.77
     rake
    -0.77
     Gujarat
    -0.76
     Blockchain
    -0.74
    bridge
    -0.73
     Brah
    -0.70
     Blumenthal
    -0.70
    rous
    -0.70
    POSITIVE LOGITS
     ult
    3.31
     Ult
    3.16
    Ult
    3.04
     Aer
    1.30
     Noct
    1.19
     Vict
    1.14
     Omn
    1.08
     Ultr
    1.08
    Ultimate
    1.04
     resolutions
    0.95
    Activations Density 0.063%

    No Known Activations