© 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. 16057
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that do not form words

    oai_token-act-pair · gpt-3.5-turbo

    alphanumeric sequences or patterns

    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
     contrace
    -0.69
     debugging
    -0.68
     closures
    -0.66
     trave
    -0.66
     upkeep
    -0.63
     refres
    -0.63
     shorth
    -0.63
     contin
    -0.62
     scrut
    -0.62
     Hort
    -0.62
    POSITIVE LOGITS
    zx
    1.23
    qq
    1.13
    Lv
    1.13
    zn
    1.05
    q
    1.04
    qt
    1.02
    OY
    1.01
    ZX
    1.01
    Rh
    1.01
    Uk
    1.01
    Activations Density 0.122%

    No Known Activations