© 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. 10-RES-JB
    11. 16581
    Prev
    Next
    INDEX
    Explanations

    alphanumeric strings with special characters

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric sequences and patterns that may indicate data or object identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sisters
    -0.73
    PATH
    -0.64
     messenger
    -0.62
     Pats
    -0.58
    Orderable
    -0.58
     affairs
    -0.58
    dayName
    -0.57
     airs
    -0.57
     Patriarch
    -0.56
     prevailing
    -0.55
    POSITIVE LOGITS
    0
    1.35
    9
    1.31
    7
    1.31
    8
    1.28
    6
    1.28
    5
    1.28
    4
    1.23
    968
    1.21
    905
    1.19
    533
    1.19
    Activations Density 0.022%

    No Known Activations