© 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. 7-RES-JB
    11. 1920
    Prev
    Next
    INDEX
    Explanations

    phrases or snippets that end with a question

    oai_token-act-pair · gpt-3.5-turbo

    the letter "L" in various contexts

    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
     mathemat
    -0.79
     Palestin
    -0.74
     elim
    -0.73
     contrace
    -0.71
     deterrent
    -0.70
     misunder
    -0.68
     scrim
    -0.68
     erad
    -0.67
     welf
    -0.66
     subscript
    -0.64
    POSITIVE LOGITS
    ï¸ı
    1.16
    tre
    0.98
    ski
    0.93
    bart
    0.87
    CEO
    0.84
    sch
    0.79
    hoe
    0.78
    tal
    0.78
    river
    0.77
    aternity
    0.77
    Activations Density 0.192%

    No Known Activations