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. 2-RES-JB
    6. 9572
    Prev
    Next
    INDEX
    Explanations

    references to physical body characteristics, particularly focusing on being slim or skinny

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "skinny" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hip
    -0.86
    oral
    -0.85
    ophen
    -0.83
    alty
    -0.82
    atory
    -0.79
    hips
    -0.77
    scl
    -0.76
    igate
    -0.75
    ant
    -0.74
    inct
    -0.74
    POSITIVE LOGITS
     skinny
    1.02
     jeans
    1.01
     dipping
    0.86
     necks
    0.85
     eater
    0.78
    bones
    0.77
     fries
    0.74
     shorts
    0.72
     strap
    0.71
     pig
    0.70
    Activations Density 0.015%

    No Known Activations