© 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. 10-RES-JB
    11. 9229
    Prev
    Next
    INDEX
    Explanations

    phrases related to permissions, rights, and access

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to access and usage rights

    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
     caution
    -0.64
     miscar
    -0.60
     panic
    -0.60
    wake
    -0.60
     goodbye
    -0.59
     knot
    -0.57
     awaited
    -0.57
     underestimate
    -0.56
     Neck
    -0.56
     awa
    -0.56
    POSITIVE LOGITS
    utenberg
    0.97
     Gutenberg
    0.79
    Digital
    0.75
     Divinity
    0.69
    lishes
    0.68
    OLOGY
    0.67
    Adult
    0.66
    archive
    0.65
    ibrarian
    0.65
    FTWARE
    0.65
    Activations Density 0.038%

    No Known Activations