© 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. 3-RES-JB
    11. 23732
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    the word "Blooming" and associated terms indicating a location or context related to it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UAL
    -0.74
     Investigative
    -0.70
    ific
    -0.69
    ial
    -0.68
     Sharks
    -0.68
    ership
    -0.66
     Pupp
    -0.65
    é¾įå¥ij士
    -0.64
    essor
    -0.63
     dilig
    -0.63
    POSITIVE LOGITS
    akening
    0.82
    wei
    0.80
    scill
    0.80
    Chart
    0.80
    bees
    0.75
    glers
    0.74
    ooming
    0.73
    hem
    0.71
    gd
    0.70
     Blooming
    0.70
    Activations Density 0.038%

    No Known Activations