© 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. 9-RES-JB
    11. 4234
    Prev
    Next
    INDEX
    Explanations

    dates and locations mentioned in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    locations and venue-related information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etheless
    -0.82
     hairs
    -0.79
    matically
    -0.78
    _.
    -0.78
     verbs
    -0.78
     macros
    -0.76
     recoil
    -0.76
     shielding
    -0.76
     weeds
    -0.76
     prey
    -0.75
    POSITIVE LOGITS
     Coliseum
    1.22
     Festival
    1.19
     Masquerade
    1.16
     TBA
    1.15
     Expo
    1.11
     Lounge
    1.08
     Club
    1.07
     Warehouse
    1.07
     Marriott
    1.04
     Auditor
    1.03
    Activations Density 0.090%

    No Known Activations