© 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. 6-RES-JB
    11. 17606
    Prev
    Next
    INDEX
    Explanations

    brain-related medical terms

    oai_token-act-pair · gpt-3.5-turbo

    names and references to specific people and entities in a context involving activities or characteristics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.63
     counsel
    -0.60
    glers
    -0.60
     Ys
    -0.59
    ught
    -0.57
     kin
    -0.57
     principals
    -0.56
     Bethesda
    -0.56
     Kislyak
    -0.54
    krit
    -0.54
    POSITIVE LOGITS
    anwhile
    0.95
    onne
    0.86
    ohyd
    0.80
    ãĤ¼ãĤ¦ãĤ¹
    0.80
    odor
    0.76
    imeter
    0.75
    azo
    0.73
    ades
    0.73
    opa
    0.71
    ã
    0.71
    Activations Density 0.075%

    No Known Activations