© 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. 7-RES-JB
    11. 17096
    Prev
    Next
    INDEX
    Explanations

    comparisons or statements emphasizing the ease of a particular action

    oai_token-act-pair · gpt-3.5-turbo

    sentences that emphasize the concept of ease or simplicity in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ulations
    -0.70
     Griffith
    -0.69
    inals
    -0.68
    anuts
    -0.67
    irrel
    -0.66
     Anthem
    -0.64
    alian
    -0.62
     Nether
    -0.61
    Ward
    -0.61
    lt
    -0.60
    POSITIVE LOGITS
     than
    1.33
     Than
    0.95
    than
    0.93
     "$:/
    0.91
     forgiving
    0.84
     compr
    0.78
     toget
    0.74
     manageable
    0.71
     prey
    0.68
    é¾įå¥ij士
    0.65
    Activations Density 0.023%

    No Known Activations