© 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. 7-RES-JB
    11. 1460
    Prev
    Next
    INDEX
    Explanations

    terms related to controversial and inflammatory language, including slurs and provocative statements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to controversial social and political identities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ispers
    -0.84
    rams
    -0.80
     suites
    -0.80
    izens
    -0.75
    Us
    -0.74
     Shots
    -0.73
    rils
    -0.73
     patches
    -0.73
     timelines
    -0.72
     Lans
    -0.72
    POSITIVE LOGITS
     whore
    0.82
     prostitute
    0.79
     unto
    0.79
    digy
    0.79
     breaker
    0.77
     himself
    0.74
     believer
    0.74
     pretending
    0.73
    atical
    0.73
    nik
    0.72
    Activations Density 0.274%

    No Known Activations