© 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. 7772
    Prev
    Next
    INDEX
    Explanations

    entities associated with various cultures, possibly people's names and geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    notated names or titles of individuals or groups

    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
    Tokens
    -0.66
    PDATE
    -0.65
     suspic
    -0.64
     challeng
    -0.64
     advoc
    -0.63
     Citiz
    -0.63
     trave
    -0.62
    icter
    -0.62
     arrang
    -0.62
     undermin
    -0.61
    POSITIVE LOGITS
     âĵĺ
    1.19
    ensis
    1.10
     (?,
    0.82
    çļĦ
    0.77
    itars
    0.75
    ;;;;;;;;;;;;
    0.73
     Quote
    0.71
    utics
    0.70
     aka
    0.69
     Originally
    0.69
    Activations Density 0.489%

    No Known Activations