© 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. 9558
    Prev
    Next
    INDEX
    Explanations

    ampersand (&) symbols in text

    oai_token-act-pair · gpt-3.5-turbo

    the symbol "&" indicating a connection or relationship between concepts

    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
    atche
    -0.81
     misunder
    -0.73
    senal
    -0.72
    etheless
    -0.70
    orable
    -0.70
    sembly
    -0.68
    ionage
    -0.65
     Leilan
    -0.63
    blance
    -0.62
    isoft
    -0.62
    POSITIVE LOGITS
    GAN
    0.84
     Friends
    0.80
    optional
    0.79
     Co
    0.78
    nect
    0.73
    #$
    0.73
     Company
    0.71
    ^^^^
    0.70
     Associates
    0.69
    ++++++++++++++++
    0.69
    Activations Density 0.047%

    No Known Activations