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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 11-RES-JB
    11. 9175
    Prev
    Next
    INDEX
    Explanations

    verbs related to adjustment and control

    oai_token-act-pair · gpt-3.5-turbo

    terms related to adjustable settings and customization options

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ublic
    -0.91
    united
    -0.80
    ét
    -0.73
    rolet
    -0.72
    ebook
    -0.71
    geries
    -0.69
    classified
    -0.69
    andro
    -0.67
    ionage
    -0.67
    illy
    -0.67
    POSITIVE LOGITS
     brightness
    1.47
     settings
    1.30
     humidity
    1.20
     parameters
    1.19
     temperature
    1.16
     thickness
    1.16
     thresholds
    1.14
     width
    1.13
     magnification
    1.13
     spacing
    1.09
    Activations Density 0.237%

    No Known Activations