© 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. 7-RES-JB
    11. 3731
    Prev
    Next
    INDEX
    Explanations

    dates and locations in a specific format

    oai_token-act-pair · gpt-3.5-turbo

    specific dates and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osate
    -0.23
     tremend
    -0.20
     þ
    -0.19
     Sty
    -0.19
     Sph
    -0.18
     Dwarf
    -0.18
    talk
    -0.18
     Py
    -0.17
     Citizen
    -0.16
     Neh
    -0.16
    POSITIVE LOGITS
    ONSORED
    0.23
    arrell
    0.20
    TPPStreamerBot
    0.20
    zens
    0.19
    irection
    0.19
    Connor
    0.19
    ibly
    0.18
    idespread
    0.18
    uable
    0.18
    ggles
    0.18
    Activations Density 11.190%

    No Known Activations