© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7-RES-JB
    11. 10984
    Prev
    Next
    INDEX
    Explanations

    names with specific patterns and characters, such as a combination of 'u' and 'Ky' with numbers

    oai_token-act-pair · gpt-3.5-turbo

    names and references related to specific individuals or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osph
    -0.64
     stump
    -0.62
     Rove
    -0.62
     defect
    -0.61
     è£ıè
    -0.59
     nons
    -0.58
     handic
    -0.58
     wounded
    -0.57
     intersection
    -0.57
     Webs
    -0.56
    POSITIVE LOGITS
    esi
    0.91
    hai
    0.82
    edu
    0.80
    oÄŁ
    0.78
    schild
    0.78
    li
    0.77
    fecture
    0.75
    vous
    0.75
    ensis
    0.72
    si
    0.69
    Activations Density 0.416%

    No Known Activations