© 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 EvalsExportsinterp-engineNEWAPI 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. 1099
    Prev
    Next
    INDEX
    Explanations

    names related to politics and events

    oai_token-act-pair · gpt-3.5-turbo

    recurring names and terms associated with popular media, particularly television and film

    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
    ĪĴ
    -0.86
    natureconservancy
    -0.84
    SPONSORED
    -0.70
     Seat
    -0.66
    atures
    -0.66
     guiActiveUnfocused
    -0.64
    imeter
    -0.64
    ħĭ
    -0.64
    imity
    -0.62
    imeters
    -0.60
    POSITIVE LOGITS
    vous
    0.91
    urga
    0.71
    andise
    0.67
     nephew
    0.64
    ourt
    0.64
    sein
    0.62
    adish
    0.62
     Frey
    0.62
    âĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪâĸĪ
    0.62
    LM
    0.61
    Activations Density 0.288%

    No Known Activations