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. 10-RES-JB
    6. 14415
    Prev
    Next
    INDEX
    Explanations

    the prefix "re-" followed by a verb

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "re-"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Edison
    -0.60
     regards
    -0.60
     Nig
    -0.60
    swer
    -0.58
     Eagle
    -0.58
     struggle
    -0.57
     extra
    -0.57
     Lords
    -0.56
     Pebble
    -0.56
     handwriting
    -0.56
    POSITIVE LOGITS
    clamation
    1.32
    ordering
    1.26
    interpret
    1.26
    thinking
    1.24
    branded
    1.23
    formation
    1.21
    aping
    1.19
    occ
    1.19
    telling
    1.19
    acqu
    1.18
    Activations Density 0.025%

    No Known Activations