© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 8043
    Prev
    Next
    INDEX
    Explanations

    the repetition of specific phrases or words within short segments of text

    oai_token-act-pair · gpt-3.5-turbo

    repeated phrases or words that convey similarity or connection

    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
    ãĤ´ãĥ³
    -0.95
    ãĤ´
    -0.85
    posted
    -0.79
     thereby
    -0.79
    claimed
    -0.79
     wherein
    -0.76
    yet
    -0.75
    cum
    -0.74
    ãĥį
    -0.73
    successfully
    -0.73
    POSITIVE LOGITS
     [
    1.21
     whole
    1.20
     guy
    1.18
     guys
    1.12
     thing
    1.08
     ['
    1.03
     stuff
    1.01
     fuckin
    0.95
     way
    0.92
     ones
    0.91
    Activations Density 0.489%

    No Known Activations