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

    Neuronpedia

    APICircuit 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. 6323
    Prev
    Next
    INDEX
    Explanations

    words related to movement with a strong emphasis on moving downward

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or themes involving downward progressions and notable individuals

    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
    âĢ¢âĢ¢âĢ¢âĢ¢
    -0.81
     dexter
    -0.72
    Lab
    -0.69
    Sensor
    -0.69
     grapp
    -0.69
     Luthor
    -0.68
    than
    -0.66
    Serv
    -0.66
     Craw
    -0.65
    acter
    -0.65
    POSITIVE LOGITS
     blah
    0.81
    rates
    0.72
     Bye
    0.68
    à¦
    0.66
    icago
    0.65
    ertility
    0.65
     GREEN
    0.64
    ãĤ¡
    0.64
    ensibly
    0.63
    enic
    0.63
    Activations Density 0.023%

    No Known Activations