© 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. 7-RES-JB
    11. 8527
    Prev
    Next
    INDEX
    Explanations

    adverbs and adjectives related to degree, intensity, or manner

    oai_token-act-pair · gpt-3.5-turbo

    adverbs related to intensity or specificity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    glers
    -0.70
    rosis
    -0.69
     Awakens
    -0.68
    yip
    -0.66
     Cause
    -0.66
     IMAGES
    -0.65
     VIDEOS
    -0.65
    ipeg
    -0.65
     willingness
    -0.63
     Thumbnails
    -0.63
    POSITIVE LOGITS
     tested
    1.05
     employed
    0.97
     evaluated
    0.96
     drawn
    0.96
     connected
    0.94
     involved
    0.94
     judged
    0.93
     situated
    0.93
     separated
    0.93
     excluded
    0.92
    Activations Density 0.189%

    No Known Activations