© 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. 0-RES-JB
    11. 4874
    Prev
    Next
    INDEX
    Explanations

    phrases related to a position or stance on a topic

    oai_token-act-pair · gpt-3.5-turbo

    terms related to opposition or adversarial positions in contexts such as politics or competition

    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
     Pog
    -0.59
     rob
    -0.59
     Yard
    -0.58
     ger
    -0.58
     vag
    -0.57
     Cheap
    -0.57
     mig
    -0.57
     Ob
    -0.57
     Redd
    -0.56
     silver
    -0.56
    POSITIVE LOGITS
    osition
    4.37
    osit
    1.29
    onents
    1.25
    etition
    1.23
    position
    1.22
    onent
    1.21
    osed
    1.18
    osite
    1.17
    onomy
    1.14
    osing
    1.13
    Activations Density 0.012%

    No Known Activations