© 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. 19351
    Prev
    Next
    INDEX
    Explanations

    numerical values

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and related data

    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
    iman
    -0.83
    kas
    -0.82
    ige
    -0.76
     Invaders
    -0.75
    IG
    -0.75
     Kik
    -0.74
     Knight
    -0.74
    uka
    -0.73
    igmatic
    -0.73
    iger
    -0.70
    POSITIVE LOGITS
    10
    1.40
     10
    1.13
    1027
    0.93
    Ten
    0.90
     1070
    0.90
    2010
    0.90
    110
    0.89
    102
    0.89
    10000
    0.88
    1016
    0.87
    Activations Density 0.155%

    No Known Activations