© 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 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. 2-RES-JB
    11. 19655
    Prev
    Next
    INDEX
    Explanations

    mentions of being a fan or enthusiast of a particular topic or person

    oai_token-act-pair · gpt-3.5-turbo

    words related to addiction or obsession

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hammad
    -0.68
     Foley
    -0.66
     Feld
    -0.66
    Fax
    -0.65
    ramid
    -0.62
     Pesh
    -0.61
    ammy
    -0.60
    stage
    -0.60
     naked
    -0.60
    RAW
    -0.58
    POSITIVE LOGITS
    icion
    1.44
    ados
    1.24
    ado
    1.04
    naire
    0.97
    folios
    0.95
    terness
    0.94
    istas
    0.87
    adoes
    0.85
    abilia
    0.84
    urus
    0.84
    Activations Density 0.013%

    No Known Activations