© 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. 4676
    Prev
    Next
    INDEX
    Explanations

    strings that seem to represent code or data, possibly with some repetition and patterns

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric characters or abbreviations

    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
     vacuum
    -0.55
     gears
    -0.55
     intentionally
    -0.55
     siege
    -0.54
     derog
    -0.53
     citations
    -0.53
     force
    -0.53
     lockout
    -0.52
     contrary
    -0.52
     tack
    -0.52
    POSITIVE LOGITS
    ZX
    1.12
    =/
    1.01
    Fu
    1.00
    Iv
    0.95
    dq
    0.94
    Ry
    0.94
    AAAAAAAA
    0.94
    ==
    0.93
    wb
    0.92
    Bs
    0.90
    Activations Density 0.031%

    No Known Activations