© 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. 6-RES-JB
    11. 10684
    Prev
    Next
    INDEX
    Explanations

    images or captions related to various subjects, such as medical services, schools, or city records

    oai_token-act-pair · gpt-3.5-turbo

    references to images or visuals associated with the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    nesia
    -0.73
    etheless
    -0.71
    DERR
    -0.69
    odder
    -0.68
     Doors
    -0.67
    iably
    -0.67
    iability
    -0.66
    cffff
    -0.65
    umper
    -0.64
    itialized
    -0.64
    POSITIVE LOGITS
     toggle
    1.16
     Courtesy
    0.98
     caption
    0.93
     IMAGES
    0.86
     screenshot
    0.80
     gallery
    0.79
     depicting
    0.79
     img
    0.75
     Caption
    0.72
     photograph
    0.72
    Activations Density 0.010%

    No Known Activations