© 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. 3758
    Prev
    Next
    INDEX
    Explanations

    phrases related to advice or life lessons

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize personal agency and responsibility

    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
    idav
    -0.75
    cellaneous
    -0.74
     confir
    -0.74
    lined
    -0.74
    umbnails
    -0.73
    SPONSORED
    -0.72
    arthed
    -0.72
    mentioned
    -0.71
    obb
    -0.71
     Explain
    -0.70
    POSITIVE LOGITS
     ALWAYS
    0.93
     NEVER
    0.86
     cannot
    0.80
     seldom
    0.78
     fundamentally
    0.78
     finite
    0.72
     sacrifices
    0.72
     outweigh
    0.71
     rarely
    0.70
     always
    0.70
    Activations Density 0.597%

    No Known Activations