Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 19575
    Prev
    Next
    INDEX
    Explanations

    names of famous individuals, particularly filmmakers such as Steven Spielberg, and terms related to psychedelic substances like LSD

    oai_token-act-pair · gpt-3.5-turbo

    mentions of notable filmmakers and substances related to mind-altering experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cit
    -0.73
     shorten
    -0.65
     shortest
    -0.65
     disorderly
    -0.63
     Flavoring
    -0.63
     expansions
    -0.62
     Virginia
    -0.62
     Alexandria
    -0.62
    cigarettes
    -0.61
    deen
    -0.61
    POSITIVE LOGITS
    istically
    1.15
    ajo
    0.93
    ists
    0.92
     Spielberg
    0.91
    identally
    0.87
    istical
    0.85
    ist
    0.82
     Chomsky
    0.81
    imei
    0.81
    idental
    0.76
    Activations Density 0.015%

    No Known Activations