© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 19374
    Prev
    Next
    INDEX
    Explanations

    proper nouns of cities and names

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and demographic information related to individuals

    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
    URI
    -0.68
     equival
    -0.67
    Catalog
    -0.63
    ELD
    -0.56
    Whit
    -0.56
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    -0.55
    itized
    -0.55
     goodbye
    -0.55
    Textures
    -0.54
    Availability
    -0.54
    POSITIVE LOGITS
     joins
    0.87
     employs
    0.85
     earns
    0.85
     insists
    0.82
     believes
    0.81
     emerged
    0.81
     enjoys
    0.81
     travelled
    0.80
     denies
    0.80
     operates
    0.79
    Activations Density 0.424%

    No Known Activations