© 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. 723
    Prev
    Next
    INDEX
    Explanations

    phrases indicating top priority or importance

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of being "number one" or top-ranking in various contexts

    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
    thia
    -0.83
    areth
    -0.79
    utic
    -0.74
    ework
    -0.72
    ifi
    -0.72
    apers
    -0.72
    ajor
    -0.72
    opian
    -0.69
    itz
    -0.69
    zan
    -0.69
    POSITIVE LOGITS
     contender
    1.25
     priority
    1.00
     trending
    0.97
     ranked
    0.90
     spot
    0.90
     ranking
    0.88
     bidder
    0.86
     rated
    0.85
     earners
    0.84
     contenders
    0.81
    Activations Density 0.034%

    No Known Activations