© 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. 15579
    Prev
    Next
    INDEX
    Explanations

    names mentioned as knowing something or being in a specific position

    oai_token-act-pair · gpt-3.5-turbo

    instances of knowledge or awareness

    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
     (~
    -0.76
    /,
    -0.73
     [*
    -0.70
     Anyway
    -0.69
     (>
    -0.69
     aforementioned
    -0.67
    ?]
    -0.67
     (=
    -0.65
     XD
    -0.65
     ([
    -0.65
    POSITIVE LOGITS
     sights
    0.82
     dreams
    0.81
     firsthand
    0.79
     dreamed
    0.77
     unforgettable
    0.76
     dream
    0.75
     marvel
    0.75
     unthinkable
    0.73
     nightmares
    0.71
     dreaming
    0.71
    Activations Density 0.981%

    No Known Activations