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. 18941
    Prev
    Next
    INDEX
    Explanations

    descriptions of physical appearance, particularly focusing on features like hair color and length

    oai_token-act-pair · gpt-3.5-turbo

    descriptive attributes related to 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
    apego
    -0.88
    duction
    -0.86
    nesday
    -0.84
    Dispatch
    -0.83
    agonist
    -0.83
    EStream
    -0.81
    arten
    -0.80
    route
    -0.79
    fail
    -0.79
    enario
    -0.79
    POSITIVE LOGITS
     translucent
    1.07
     robes
    1.07
     protr
    1.03
     shimmer
    1.02
     wrink
    0.98
     accents
    0.93
     tint
    0.93
     sleek
    0.93
     adorned
    0.92
     hood
    0.91
    Activations Density 0.591%

    No Known Activations