© 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. 8-RES-JB
    11. 23885
    Prev
    Next
    INDEX
    Explanations

    versions of software such as operating systems and programming languages followed by their version numbers

    oai_token-act-pair · gpt-3.5-turbo

    numerical versions or updates related to software or operating systems

    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
    rolet
    -0.75
     motel
    -0.70
    ierrez
    -0.68
    directed
    -0.68
     Nanto
    -0.68
     flyer
    -0.68
     hypot
    -0.66
    çĶ°
    -0.66
     PRESS
    -0.65
    bery
    -0.65
    POSITIVE LOGITS
    Version
    1.00
    beta
    0.94
    +,
    0.92
     upgr
    0.89
     SDK
    0.88
     compatibility
    0.88
    xx
    0.87
     compatible
    0.86
     deprecated
    0.82
    +)
    0.80
    Activations Density 0.085%

    No Known Activations