© 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. 8-RES-JB
    11. 8230
    Prev
    Next
    INDEX
    Explanations

    numeric values with units

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to statistics or metrics

    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
    actionDate
    -0.76
    bara
    -0.63
    ierrez
    -0.62
    £ı
    -0.62
     forcefully
    -0.60
     periodically
    -0.60
     reintrodu
    -0.60
    leased
    -0.59
    rame
    -0.59
     occasional
    -0.58
    POSITIVE LOGITS
    990
    1.00
    9999
    0.99
    75
    0.95
    66
    0.94
    80
    0.94
    000000
    0.93
    70
    0.93
    800
    0.93
    67
    0.93
    200
    0.92
    Activations Density 0.342%

    No Known Activations