© 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. 7620
    Prev
    Next
    INDEX
    Explanations

    titles of movies or songs

    oai_token-act-pair · gpt-3.5-turbo

    song titles

    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
     cryptocurrency
    -0.84
     listed
    -0.80
     bitcoin
    -0.77
     relatively
    -0.76
     largely
    -0.74
     describe
    -0.74
     blockchain
    -0.73
     substantive
    -0.73
     telecommunications
    -0.73
     informative
    -0.73
    POSITIVE LOGITS
     Bounce
    1.07
     Fever
    1.03
    ĸļ
    1.02
     Mama
    1.01
     Breaker
    1.01
     Lover
    1.00
     Balloon
    1.00
     Wheels
    0.97
     Thro
    0.97
     Trouble
    0.97
    Activations Density 0.381%

    No Known Activations