© 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. 7-RES-JB
    11. 12653
    Prev
    Next
    INDEX
    Explanations

    highlighted information or key points in a story

    oai_token-act-pair · gpt-3.5-turbo

    terms related to news highlights and key points

    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
    ogly
    -0.80
     nurs
    -0.79
    unci
    -0.76
    abase
    -0.73
    tails
    -0.71
    akings
    -0.67
    è¦ļéĨĴ
    -0.67
    haps
    -0.66
     nib
    -0.65
    urat
    -0.65
    POSITIVE LOGITS
     ï
    0.85
     WATCHED
    0.81
     IMAGES
    0.77
     Surveillance
    0.77
     Kaine
    0.74
     Timeline
    0.73
     WATCH
    0.71
     Highlights
    0.70
     Ùħ
    0.68
    =>
    0.68
    Activations Density 0.012%

    No Known Activations