© 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. 6-RES-JB
    11. 10756
    Prev
    Next
    INDEX
    Explanations

    words related to legal and social issues

    oai_token-act-pair · gpt-3.5-turbo

    issues related to discrimination and rights, particularly concerning sex work

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĶ°
    -0.61
    henko
    -0.60
    çīĪ
    -0.58
    kered
    -0.56
    DragonMagazine
    -0.54
    udos
    -0.54
    xtap
    -0.54
    ragon
    -0.54
     aback
    -0.53
    00007
    -0.53
    POSITIVE LOGITS
     certain
    0.65
     various
    0.63
     human
    0.61
     slavery
    0.60
     oppression
    0.58
     capitalism
    0.58
     healthcare
    0.58
     such
    0.57
     their
    0.57
     humans
    0.56
    Activations Density 1.136%

    No Known Activations