© 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 EvalsExportsinterp-engineNEWAPI 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. 10414
    Prev
    Next
    INDEX
    Explanations

    references to memorabilia and items associated with memory

    oai_token-act-pair · gpt-3.5-turbo

    references to memory and memorabilia

    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
    bringer
    -0.72
    IRO
    -0.70
     Dani
    -0.69
    OHN
    -0.68
    ï¸
    -0.65
    redd
    -0.62
     Nah
    -0.61
    sided
    -0.59
     Canary
    -0.58
     Diver
    -0.58
    POSITIVE LOGITS
    abilia
    1.85
    izable
    1.32
    isable
    1.29
    andum
    1.24
    izations
    1.19
    ized
    1.18
    ization
    1.17
    ably
    1.15
    izing
    1.12
    isation
    1.10
    Activations Density 0.068%

    No Known Activations