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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RES-JB
    6. 19555
    Prev
    Next
    INDEX
    Explanations

    gender-specific possessive pronouns followed by body parts

    oai_token-act-pair · gpt-3.5-turbo

    references to possession and familial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ablishment
    -0.91
    iliate
    -0.75
     Massacre
    -0.73
     Meadows
    -0.72
    ancial
    -0.70
     Recomm
    -0.69
     Invasion
    -0.66
    ãĥ´ãĤ¡
    -0.65
    ete
    -0.65
    WAR
    -0.64
    POSITIVE LOGITS
     palms
    1.47
     knees
    1.42
     hips
    1.42
     fingertips
    1.41
     chin
    1.40
     fingers
    1.38
     elbows
    1.35
     arms
    1.35
     fists
    1.35
     gaze
    1.34
    Activations Density 0.116%

    No Known Activations