© 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. 0-RES-JB
    11. 4105
    Prev
    Next
    INDEX
    Explanations

    mentions of exclusion or exclusivity in a text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to social and political exclusion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vier
    -0.65
    @@
    -0.63
    ved
    -0.62
     Whis
    -0.62
    Master
    -0.62
     Rider
    -0.61
    Snow
    -0.60
     Whats
    -0.59
     Reaper
    -0.59
     Anon
    -0.59
    POSITIVE LOGITS
     exclusion
    4.11
     exclus
    1.88
     inclusion
    1.73
     exclude
    1.73
     excluded
    1.63
    clusion
    1.52
     omission
    1.41
     excludes
    1.37
     exemption
    1.32
     avoidance
    1.29
    Activations Density 0.017%

    No Known Activations