© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1988
    Prev
    Next
    INDEX
    Explanations

    verbs related to distinguishing, differentiating, or separating different entities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to distinguishing or differentiating between entities or concepts

    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
     Omni
    -0.67
     Fulton
    -0.65
     Apostles
    -0.65
    ORE
    -0.62
    Assembly
    -0.62
     havoc
    -0.59
    Mos
    -0.59
    MN
    -0.59
    onz
    -0.58
    amar
    -0.57
    POSITIVE LOGITS
     between
    1.09
    ively
    0.96
     Between
    0.96
    iates
    0.95
    iveness
    0.92
    between
    0.86
     distinctions
    0.86
     distinguish
    0.85
     distinguishing
    0.84
     sexes
    0.83
    Activations Density 0.050%

    No Known Activations