© 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. 720
    Prev
    Next
    INDEX
    Explanations

    mentions of specific attire or clothing items

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "pantheon."

    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
     Carbuncle
    -0.83
    UTION
    -0.70
     Jav
    -0.70
     Sett
    -0.70
    displayText
    -0.68
    MK
    -0.65
    upon
    -0.65
    ADE
    -0.63
     Hitman
    -0.63
    FINE
    -0.63
    POSITIVE LOGITS
    heon
    1.40
     pant
    1.22
    icip
    0.95
    agraph
    0.93
    ry
    0.88
    hetically
    0.86
    oleon
    0.82
    agonist
    0.81
    pants
    0.80
    archy
    0.80
    Activations Density 0.004%

    No Known Activations