© 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. 16687
    Prev
    Next
    INDEX
    Explanations

    phrases describing distinct or individual characteristics of different items or entities

    oai_token-act-pair · gpt-3.5-turbo

    elements representing individual items or instances within a collective context

    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
     abound
    -0.70
    haven
    -0.65
    essors
    -0.63
    ync
    -0.62
    WM
    -0.59
    ONT
    -0.58
    paren
    -0.58
    ibur
    -0.57
    yout
    -0.57
    Ws
    -0.57
    POSITIVE LOGITS
     individually
    1.47
     separately
    1.21
     independently
    1.00
     unique
    0.97
     differently
    0.93
     varying
    0.91
     uniquely
    0.89
     differing
    0.88
     distinct
    0.87
     different
    0.86
    Activations Density 0.335%

    No Known Activations