© 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. 8-RES-JB
    11. 15195
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "adult"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "adult" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atility
    -0.83
    adr
    -0.77
    ãĤ¡
    -0.74
    gments
    -0.74
    arity
    -0.72
     Cosponsors
    -0.72
     Klux
    -0.71
    gment
    -0.70
    wark
    -0.70
    externalActionCode
    -0.69
    POSITIVE LOGITS
    erer
    1.06
    erers
    1.03
     Swim
    1.00
     diapers
    0.88
     supervision
    0.85
     beverages
    0.85
    ager
    0.82
     male
    0.81
     males
    0.79
    hetical
    0.77
    Activations Density 0.040%

    No Known Activations