© 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. 8-RES-JB
    11. 17816
    Prev
    Next
    INDEX
    Explanations

    captions from photo galleries

    oai_token-act-pair · gpt-3.5-turbo

    segments related to photo captions or multimedia content

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     attrition
    -0.77
    bage
    -0.75
    soType
    -0.73
    nexus
    -0.70
     expectation
    -0.69
    nesia
    -0.67
    ministic
    -0.66
     sooner
    -0.66
    riction
    -0.65
    heit
    -0.64
    POSITIVE LOGITS
     Faces
    1.05
     Scenes
    0.93
     Photos
    0.89
     Stru
    0.79
     Gad
    0.77
     Top
    0.75
     Countries
    0.74
     ï
    0.73
     Shows
    0.72
     Meet
    0.71
    Activations Density 0.049%

    No Known Activations