© 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. 13668
    Prev
    Next
    INDEX
    Explanations

    words related to different forms of gambling or chance

    oai_token-act-pair · gpt-3.5-turbo

    repeated occurrences of the letter 'l'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     lawy
    -0.66
     Vald
    -0.65
    chell
    -0.62
     Lit
    -0.61
     Credit
    -0.61
     Shack
    -0.61
     Primal
    -0.60
     Bots
    -0.59
     Parenthood
    -0.58
    ãĥ¯ãĥ³
    -0.58
    POSITIVE LOGITS
    ibrarian
    1.47
    adders
    1.38
    ibr
    1.32
    ivery
    1.24
    ongh
    1.21
    asso
    1.18
    onel
    1.18
    izards
    1.16
    acer
    1.14
    ighth
    1.13
    Activations Density 0.020%

    No Known Activations