© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20321
    Prev
    Next
    INDEX
    Explanations

    phrases related to sketch-like descriptions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sketches and sketching

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rogens
    -0.82
     Fenrir
    -0.67
     iod
    -0.65
    judicial
    -0.64
    çĦ
    -0.62
    undai
    -0.62
    Ïī
    -0.61
    riott
    -0.60
     Angola
    -0.60
    onso
    -0.59
    POSITIVE LOGITS
     sketch
    1.01
     sketches
    0.98
    book
    0.92
    smanship
    0.90
    pad
    0.84
    y
    0.83
    BOOK
    0.82
    books
    0.81
    eers
    0.79
    enegger
    0.78
    Activations Density 0.032%

    No Known Activations