© 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. 12140
    Prev
    Next
    INDEX
    Explanations

    words related to ideologies or beliefs

    oai_token-act-pair · gpt-3.5-turbo

    terms related to ideology and political themes

    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
    rooms
    -0.90
    fully
    -0.87
    ources
    -0.75
    terday
    -0.75
    backs
    -0.69
    pool
    -0.69
    ebook
    -0.68
    pit
    -0.67
    ells
    -0.67
    âķIJâķIJ
    -0.66
    POSITIVE LOGITS
    eering
    0.78
    ovic
    0.77
    achi
    0.75
    umerable
    0.74
    nox
    0.72
    ividual
    0.71
    itial
    0.70
    cest
    0.70
    otin
    0.69
    ATIVE
    0.68
    Activations Density 0.134%

    No Known Activations