© 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. 6969
    Prev
    Next
    INDEX
    Explanations

    adjectives describing the quality or impact of a situation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positive or negative outcomes related to policies and news

    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
    racuse
    -0.82
    hyde
    -0.79
    opers
    -0.76
    letes
    -0.72
    avorite
    -0.71
    uckle
    -0.70
    onds
    -0.70
    agos
    -0.70
    lete
    -0.67
    irez
    -0.65
    POSITIVE LOGITS
     news
    1.28
     publicity
    1.17
     manners
    0.98
    news
    0.95
    bye
    0.94
     luck
    0.94
     enough
    0.92
     optics
    0.92
     karma
    0.91
     NEWS
    0.89
    Activations Density 0.092%

    No Known Activations