© 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. 9-RES-JB
    11. 5410
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names and terms, likely related to a particular topic or theme

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matically
    -1.03
    pec
    -0.84
    ¶æ
    -0.83
    ments
    -0.81
    ment
    -0.79
    mercial
    -0.78
    ming
    -0.76
    asing
    -0.76
    pee
    -0.75
    gdala
    -0.73
    POSITIVE LOGITS
     Diesel
    0.70
     Bagg
    0.66
    edit
    0.63
    ersen
    0.63
    icz
    0.62
     laundry
    0.61
     Lakes
    0.61
    DragonMagazine
    0.61
     Meier
    0.60
    amily
    0.59
    Activations Density 0.117%

    No Known Activations