© 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. 9876
    Prev
    Next
    INDEX
    Explanations

    negations related to an action or event

    oai_token-act-pair · gpt-3.5-turbo

    negative statements concerning the existence or inclusion of certain elements or conditions

    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
     restless
    -0.75
     unlucky
    -0.73
     watching
    -0.72
     Watching
    -0.71
     glad
    -0.68
     Mayhem
    -0.68
     minds
    -0.66
     hobbies
    -0.66
    rolled
    -0.64
     lucky
    -0.63
    POSITIVE LOGITS
     contain
    1.67
     include
    1.48
     involve
    1.48
     encompass
    1.40
     incorporate
    1.37
     entail
    1.28
     Include
    1.21
    include
    1.20
     reflect
    1.19
     depict
    1.18
    Activations Density 0.201%

    No Known Activations