© 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. 11-RES-JB
    11. 2501
    Prev
    Next
    INDEX
    Explanations

    phrases expressing opinions or evaluations

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating the presence and importance of specific qualities or conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    heid
    -0.70
    neys
    -0.67
    enne
    -0.67
    azon
    -0.65
    perty
    -0.65
    igraph
    -0.65
    imeters
    -0.64
     Associates
    -0.63
    iphate
    -0.62
     Travels
    -0.62
    POSITIVE LOGITS
     understandable
    1.15
     testament
    1.08
     unfortunate
    1.06
     why
    1.03
     partly
    0.99
     disappointing
    0.98
     unsur
    0.96
     frustrating
    0.95
     discouraging
    0.93
     exacerbated
    0.93
    Activations Density 0.180%

    No Known Activations