© 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. 0-RES-JB
    11. 12831
    Prev
    Next
    INDEX
    Explanations

    special characters that typically indicate a specific language or encoding

    oai_token-act-pair · gpt-3.5-turbo

    special 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 @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     calendars
    -0.66
     Gin
    -0.65
     Glou
    -0.64
     condoms
    -0.62
    ointed
    -0.61
     foil
    -0.61
     gag
    -0.61
     DVD
    -0.59
    backs
    -0.59
     practice
    -0.59
    POSITIVE LOGITS
    º
    4.57
    »
    2.22
    ¼
    1.83
    ¿
    1.82
    ¸
    1.81
    ¹
    1.79
    ¶
    1.76
    ²
    1.75
    ´
    1.73
    ¾
    1.73
    Activations Density 0.010%

    No Known Activations