© 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. 6100
    Prev
    Next
    INDEX
    Explanations

    phrases related to claims or assertions of identity or status

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    phrases where someone is making a claim

    oai_token-act-pair · gpt-3.5-turbo
    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
    furt
    -0.71
    course
    -0.70
    bats
    -0.65
    specified
    -0.65
    noticed
    -0.65
    river
    -0.63
    apps
    -0.60
     Rapids
    -0.58
    cart
    -0.58
    items
    -0.57
    POSITIVE LOGITS
     specialize
    0.96
     embody
    0.89
     represent
    0.88
     derive
    0.86
     be
    0.85
     recreate
    0.85
     perform
    0.80
     solve
    0.80
     speak
    0.80
     have
    0.80
    Activations Density 0.034%

    No Known Activations