© 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. 1-RES-JB
    11. 24235
    Prev
    Next
    INDEX
    Explanations

    phrases related to businesses or companies

    oai_token-act-pair · gpt-3.5-turbo

    the ampersand symbol '&' used in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -1.01
    ilitary
    -0.80
    senal
    -0.79
    atche
    -0.76
    owicz
    -0.73
    ionage
    -0.72
    govtrack
    -0.70
     Leilan
    -0.69
     misunder
    -0.69
    anqu
    -0.67
    POSITIVE LOGITS
    #$
    0.94
    NAS
    0.82
    etc
    0.81
    vine
    0.79
    ++++++++++++++++
    0.79
     vice
    0.77
    GAN
    0.77
     Associates
    0.76
    optional
    0.71
    Corp
    0.69
    Activations Density 0.063%

    No Known Activations