© 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. 12580
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals or businesses

    oai_token-act-pair · gpt-3.5-turbo

    references to David Bowie and concepts related to tailoring and laundry

    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
    essee
    -0.98
    ica
    -0.89
    ivity
    -0.87
    ative
    -0.86
    oran
    -0.85
    ions
    -0.83
    ansas
    -0.82
    icals
    -0.81
    iva
    -0.81
    ivities
    -0.80
    POSITIVE LOGITS
     blinded
    0.71
    BALL
    0.69
     Peninsula
    0.67
    mercial
    0.67
    pton
    0.67
     Wilde
    0.65
     propriet
    0.64
     lodge
    0.62
    plete
    0.61
    yang
    0.60
    Activations Density 0.109%

    No Known Activations