© 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. 8-RES-JB
    11. 6822
    Prev
    Next
    INDEX
    Explanations

    positive words or expressions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of positivity and positive sentiment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loo
    -0.84
     Brilliant
    -0.71
    HAEL
    -0.70
    opsy
    -0.70
    Leod
    -0.68
    tracks
    -0.68
    wine
    -0.66
     Hearts
    -0.63
     Recall
    -0.62
    stall
    -0.62
    POSITIVE LOGITS
    itional
    1.51
    itions
    1.34
    itivity
    1.26
    idon
    1.15
    itionally
    1.13
    itory
    1.10
    itiveness
    1.07
    itor
    1.06
    ited
    1.04
    icion
    1.03
    Activations Density 0.029%

    No Known Activations