© 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. 21095
    Prev
    Next
    INDEX
    Explanations

    percentage changes in numerical values

    oai_token-act-pair · gpt-3.5-turbo

    statistical data and percentages related to changes or trends

    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
    tags
    -0.90
    ateurs
    -0.83
    devices
    -0.78
    bits
    -0.77
    sels
    -0.77
    rencies
    -0.76
    isms
    -0.76
    stocks
    -0.74
     Techniques
    -0.74
    rients
    -0.74
    POSITIVE LOGITS
     multiplier
    0.92
     improvement
    0.90
     deficit
    0.90
     spike
    0.87
     ratio
    0.86
     presence
    0.86
     barrier
    0.85
    omination
    0.84
     increase
    0.83
     uptick
    0.82
    Activations Density 0.152%

    No Known Activations