Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 9952
    Prev
    Next
    INDEX
    Explanations

    references related to gender identity and declarations of identity

    oai_token-act-pair · gpt-3.5-turbo

    terms related to gender identity and restroom use policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Luck
    -0.87
     Appl
    -0.81
     playbook
    -0.79
     cellar
    -0.78
     Buffett
    -0.77
     Roose
    -0.73
     Luck
    -0.73
     Lans
    -0.72
    Fail
    -0.72
     auctions
    -0.71
    POSITIVE LOGITS
    gender
    1.53
     genders
    1.52
     gender
    1.43
     transgender
    1.41
     transsexual
    1.39
     pronouns
    1.39
     Transgender
    1.33
     genital
    1.32
     genitals
    1.29
    Gender
    1.27
    Activations Density 0.441%

    No Known Activations