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. 751
    Prev
    Next
    INDEX
    Explanations

    words ending in "urs" or "ursing"

    oai_token-act-pair · gpt-3.5-turbo

    forms of the word "reimburse" or similar variations related to reimbursement

    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
     booth
    -0.64
     gauge
    -0.63
     Breaking
    -0.62
     breaking
    -0.62
     angle
    -0.62
     busted
    -0.60
     Morse
    -0.60
     cooler
    -0.60
     overpowered
    -0.58
     Kelly
    -0.57
    POSITIVE LOGITS
    urs
    4.61
    urred
    2.10
    ur
    1.98
    urring
    1.96
    urses
    1.86
    urse
    1.51
    UR
    1.48
    ursed
    1.35
    urt
    1.32
    ural
    1.26
    Activations Density 0.013%

    No Known Activations