© 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. 19300
    Prev
    Next
    INDEX
    Explanations

    positive adjectives describing various concepts, such as good, great, fitting, hard, deeper, easy, and imperfect

    oai_token-act-pair · gpt-3.5-turbo

    sentiments and evaluations related to quality and 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
    selected
    -0.68
     Tripoli
    -0.68
     Hemp
    -0.65
    oided
    -0.64
     Pax
    -0.62
    arcity
    -0.61
    rane
    -0.60
     Nether
    -0.59
     Roche
    -0.58
    rongh
    -0.57
    POSITIVE LOGITS
    âĢ
    1.43
    ðŁ
    1.12
     ðŁij
    1.11
    ðŁĺ
    1.09
    ðŁij
    1.03
    âľ
    1.03
    ¨
    1.02
    âĻ
    1.01
    âĺ
    1.01
    !!!!
    1.00
    Activations Density 0.385%

    No Known Activations