© 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. 1-RES-JB
    11. 20043
    Prev
    Next
    INDEX
    Explanations

    words related to hormones and gender-specific facilities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hormones, specifically testosterone and its associated contexts, particularly regarding gender and restroom issues

    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
    uncture
    -0.80
    natureconservancy
    -0.74
    keyes
    -0.74
    tin
    -0.72
    akening
    -0.71
    steen
    -0.71
    Assembly
    -0.70
    otin
    -0.69
     Coul
    -0.68
    ricanes
    -0.67
    POSITIVE LOGITS
    xual
    1.11
     estrogen
    0.84
     testosterone
    0.80
    gender
    0.79
     transsexual
    0.76
    opausal
    0.76
     ejac
    0.74
     Gemini
    0.74
    士
    0.72
     Jenner
    0.72
    Activations Density 0.020%

    No Known Activations