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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 10052
    Prev
    Next
    INDEX
    Explanations

    words related to physical appearance, particularly focusing on weight and body shape

    oai_token-act-pair · gpt-3.5-turbo

    terms related to body size and physical appearance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ative
    -0.88
    iller
    -0.88
    esian
    -0.83
    inations
    -0.83
    enary
    -0.80
    argon
    -0.79
    ataka
    -0.79
    atography
    -0.78
    ophers
    -0.78
    endez
    -0.77
    POSITIVE LOGITS
    bum
    0.96
    LOAD
    0.85
     cheeks
    0.80
    Bey
    0.75
     belly
    0.74
     Fool
    0.70
    GROUND
    0.70
    button
    0.70
    buck
    0.69
    poke
    0.69
    Activations Density 0.054%

    No Known Activations