© 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. 10-RES-JB
    11. 11492
    Prev
    Next
    INDEX
    Explanations

    political and societal topics of discussion

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to societal beliefs and moral perceptions

    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
    adel
    -0.73
    çīĪ
    -0.72
    ierrez
    -0.63
    mentioned
    -0.63
    arthed
    -0.61
    rawdownloadcloneembedreportprint
    -0.59
    ourney
    -0.57
     sidx
    -0.57
    idav
    -0.57
     aback
    -0.57
    POSITIVE LOGITS
     somehow
    0.95
     morally
    0.93
     infall
    0.84
     inherently
    0.83
     superior
    0.82
     immutable
    0.81
     oppressed
    0.79
     innate
    0.79
     evils
    0.78
     sufficiently
    0.78
    Activations Density 0.840%

    No Known Activations