© 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. 2773
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal reflections or anecdotes

    oai_token-act-pair · gpt-3.5-turbo

    segments indicating ongoing dialogue or conversation

    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
     worthless
    -0.77
     enraged
    -0.72
     gall
    -0.72
     unsc
    -0.71
     lawfully
    -0.71
     capit
    -0.71
     unin
    -0.71
     futile
    -0.70
    wart
    -0.70
     equivalent
    -0.70
    POSITIVE LOGITS
    Interview
    1.27
    Question
    1.19
    Were
    1.19
    Yeah
    1.16
    Narr
    1.15
    Asked
    1.14
    Anyway
    1.10
    Talking
    1.08
    Was
    1.07
    Anything
    1.07
    Activations Density 0.386%

    No Known Activations