© 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. 10903
    Prev
    Next
    INDEX
    Explanations

    proper nouns, specifically names of places and people

    oai_token-act-pair · gpt-3.5-turbo

    references to specific geographic locations and entities

    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
    "]
    -0.63
    death
    -0.62
    "],"
    -0.60
    ODY
    -0.59
     withd
    -0.58
    sal
    -0.58
    lass
    -0.58
    lus
    -0.57
     behalf
    -0.57
    gression
    -0.57
    POSITIVE LOGITS
     hovering
    0.86
     intervening
    0.82
     topping
    0.81
     buzzing
    0.79
     doubling
    0.79
     looming
    0.77
     hooked
    0.77
     spilling
    0.77
     popping
    0.75
     flourish
    0.74
    Activations Density 0.421%

    No Known Activations