© 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. 9-RES-JB
    11. 18643
    Prev
    Next
    INDEX
    Explanations

    phrases indicating comparison or contrast

    oai_token-act-pair · gpt-3.5-turbo

    instances of phrases indicating that someone or something is not the only one of its kind

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    only
    -0.78
     until
    -0.69
     ONLY
    -0.69
    Only
    -0.66
     EVEN
    -0.66
     +++
    -0.66
    thood
    -0.66
     ALWAYS
    -0.65
     Only
    -0.64
    >>\
    -0.64
    POSITIVE LOGITS
     troubled
    0.77
     woes
    0.77
     disgruntled
    0.73
     questionable
    0.71
     bizarre
    0.71
     politic
    0.70
     misfortune
    0.70
     grievances
    0.70
     trouble
    0.69
     struggles
    0.69
    Activations Density 0.315%

    No Known Activations