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. 0-RES-JB
    6. 62
    Prev
    Next
    INDEX
    Explanations

    terms related to significant increase or success

    oai_token-act-pair · gpt-3.5-turbo

    words related to significant increases or decreases in value or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fil
    -0.69
     Brus
    -0.69
     oral
    -0.67
     Nic
    -0.66
     recess
    -0.65
    film
    -0.63
    construct
    -0.62
    dit
    -0.62
     edit
    -0.62
    DS
    -0.62
    POSITIVE LOGITS
     soaring
    2.95
     soar
    2.88
     soared
    2.83
     plummet
    2.31
     skyrocket
    2.18
     plummeted
    1.99
     surged
    1.75
     surging
    1.74
     spir
    1.62
     plung
    1.44
    Activations Density 0.031%

    No Known Activations