© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 1937
    Prev
    Next
    INDEX
    Explanations

    screen sizes indicated in inches

    oai_token-act-pair · gpt-3.5-turbo

    screen size specifications in inches

    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
    REDACTED
    -0.78
    sterdam
    -0.75
    erg
    -0.71
    hran
    -0.67
     Trafford
    -0.66
    brates
    -0.65
    funding
    -0.65
    killed
    -0.65
    govern
    -0.64
    given
    -0.63
    POSITIVE LOGITS
    itude
    0.87
    itudinal
    0.81
     increments
    0.72
     MacBook
    0.72
    ometer
    0.72
     angle
    0.70
    apixel
    0.70
     heights
    0.69
     floppy
    0.68
     versions
    0.68
    Activations Density 0.034%

    No Known Activations