© 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. 10-RES-JB
    11. 16112
    Prev
    Next
    INDEX
    Explanations

    versions of software

    oai_token-act-pair · gpt-3.5-turbo

    references to software versions and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Telegraph
    -0.64
     motivational
    -0.63
     motel
    -0.62
     forfeit
    -0.62
     humid
    -0.61
     Hammond
    -0.61
     vacated
    -0.60
     sentimental
    -0.59
     amy
    -0.58
    idium
    -0.56
    POSITIVE LOGITS
    beta
    1.20
    Beta
    0.93
    Version
    0.91
    version
    0.89
    alpha
    0.89
    xx
    0.88
     beta
    0.86
     Beta
    0.85
    Release
    0.83
     Version
    0.82
    Activations Density 0.065%

    No Known Activations