© 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. 16803
    Prev
    Next
    INDEX
    Explanations

    the word "Mac" followed by a number from 9 to 10

    oai_token-act-pair · gpt-3.5-turbo

    the name "Mac" in various 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
     NETWORK
    -0.67
    uated
    -0.66
     ECB
    -0.61
     ditch
    -0.59
     balloons
    -0.59
    ãĥĥãĥĪ
    -0.59
     Gundam
    -0.58
    ãĥĦ
    -0.58
    glers
    -0.58
     BDS
    -0.57
    POSITIVE LOGITS
    intosh
    1.34
    donald
    1.23
    abre
    1.19
    Leod
    1.13
    pher
    1.09
    Lean
    1.03
    lean
    1.02
    artney
    0.99
    Kay
    0.95
    ross
    0.93
    Activations Density 0.011%

    No Known Activations