© 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. 9-RES-JB
    11. 10028
    Prev
    Next
    INDEX
    Explanations

    information related to academic institutions and research institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to academic institutions and organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     colours
    -0.90
     coloured
    -0.88
     organising
    -0.87
     spo
    -0.82
     Maid
    -0.81
     fulfil
    -0.80
     vict
    -0.77
     favourite
    -0.76
     endeavour
    -0.75
     favour
    -0.75
    POSITIVE LOGITS
    Researchers
    1.04
    conom
    0.99
    Americans
    0.99
    Companies
    0.93
    Bloomberg
    0.92
    Abstract
    0.92
    osate
    0.84
    Scientists
    0.84
     Researchers
    0.83
    Bitcoin
    0.82
    Activations Density 0.911%

    No Known Activations