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. 22123
    Prev
    Next
    INDEX
    Explanations

    phrases related to percentages and numerical values

    oai_token-act-pair · gpt-3.5-turbo

    the word "over" in various contexts, particularly in relation to quantities or comparisons

    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
     Soc
    -0.65
     licensed
    -0.60
     societies
    -0.59
     clenched
    -0.58
     lam
    -0.56
     grind
    -0.55
     stat
    -0.55
     beads
    -0.54
     Stats
    -0.54
     endeav
    -0.54
    POSITIVE LOGITS
    over
    4.27
    overs
    3.49
    OVER
    2.44
    Over
    1.70
     overs
    1.42
     Over
    1.38
     OVER
    1.37
    around
    1.31
    under
    1.28
     over
    1.14
    Activations Density 0.011%

    No Known Activations