© 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. 6-RES-JB
    11. 7952
    Prev
    Next
    INDEX
    Explanations

    strings that are likely the result of encoding or data processing operations, such as database entries

    oai_token-act-pair · gpt-3.5-turbo

    repeated characters or symbols in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     maxim
    -0.71
    anwhile
    -0.68
    ãĥ¯ãĥ³
    -0.67
    digit
    -0.66
     minim
    -0.65
    secut
    -0.61
    ULT
    -0.60
    hog
    -0.59
     panc
    -0.59
     mant
    -0.59
    POSITIVE LOGITS
    Ŀ
    1.04
    ¡
    1.01
    £
    0.98
    Ĵ
    0.98
    ĺ
    0.92
    ¦
    0.91
    Ķ
    0.89
    į
    0.86
    ¥
    0.85
    IJ
    0.85
    Activations Density 0.260%

    No Known Activations