© 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. 8-RES-JB
    11. 10118
    Prev
    Next
    INDEX
    Explanations

    names and mentions related to the name "Rob"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Rob"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAYS
    -0.77
     fu
    -0.71
    ":[
    -0.69
    uated
    -0.68
     halls
    -0.67
    CVE
    -0.64
    SEE
    -0.63
    xual
    -0.62
     seriousness
    -0.60
     fluoride
    -0.59
    POSITIVE LOGITS
    bie
    1.16
    bery
    1.12
    otic
    1.10
    shaw
    1.09
    otics
    1.09
    bers
    1.06
    bing
    1.04
    inson
    0.99
    otech
    0.98
    bies
    0.94
    Activations Density 0.021%

    No Known Activations