© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 8635
    Prev
    Next
    INDEX
    Explanations

    terms related to male gender or characteristics

    oai_token-act-pair · gpt-3.5-turbo

    references to male individuals, particularly in the context of their behaviors and relationships with females

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lich
    -0.81
    Account
    -0.70
    Pal
    -0.69
    Haunted
    -0.69
    ãĤ·ãĥ£
    -0.67
    breaking
    -0.67
    Journal
    -0.66
    sy
    -0.66
    lined
    -0.65
    TABLE
    -0.65
    POSITIVE LOGITS
     Males
    1.10
     Females
    1.05
     males
    0.96
    xual
    0.92
     females
    0.84
    aurus
    0.83
    ignty
    0.79
    cius
    0.78
    paces
    0.75
     mating
    0.75
    Activations Density 0.013%

    No Known Activations