© 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. 10-RES-JB
    11. 12910
    Prev
    Next
    INDEX
    Explanations

    specific rankings or positions within a certain context

    oai_token-act-pair · gpt-3.5-turbo

    terms and phrases related to rankings and positions in a hierarchy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shutterstock
    -0.74
    quit
    -0.72
    enegger
    -0.68
    DCS
    -0.66
    ripp
    -0.65
     Cheong
    -0.64
    urations
    -0.63
     Stella
    -0.63
    uphem
    -0.62
    govtrack
    -0.59
    POSITIVE LOGITS
     tier
    1.08
     bracket
    0.98
     spot
    0.93
     tiers
    0.89
     drawer
    0.89
    liga
    0.88
     scorer
    0.88
     contenders
    0.87
     division
    0.87
     earners
    0.85
    Activations Density 0.063%

    No Known Activations