© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 18739
    Prev
    Next
    INDEX
    Explanations

    words or phrases emphasizing intensity or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    the frequency of the word "very" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ¨ãĥ«
    -0.64
     Cases
    -0.62
     Landing
    -0.62
     Mechdragon
    -0.59
    %:
    -0.59
     Companies
    -0.58
     Cosponsors
    -0.55
     WTC
    -0.55
     guiActiveUn
    -0.55
     waivers
    -0.55
    POSITIVE LOGITS
     uh
    0.76
     um
    0.74
    ruly
    0.74
    ribly
    0.67
    nery
    0.65
    acid
    0.64
    itates
    0.62
     noticeably
    0.62
    lot
    0.61
    parable
    0.60
    Activations Density 0.051%

    No Known Activations