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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7-RES-JB
    6. 15639
    Prev
    Next
    INDEX
    Explanations

    terms related to physical attributes or characteristics, specifically related to skin, pepper spray, acid, and razor

    oai_token-act-pair · gpt-3.5-turbo

    terms related to skin and various substances or conditions associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Transparency
    -0.67
    kson
    -0.65
     Dresden
    -0.65
    Reloaded
    -0.64
    CVE
    -0.64
    HCR
    -0.63
     Governors
    -0.63
    ADRA
    -0.62
     Directions
    -0.62
     Hendricks
    -0.62
    POSITIVE LOGITS
    bag
    0.95
    pipe
    0.91
    neck
    0.88
    bowl
    0.87
    wagon
    0.86
    horn
    0.83
    bl
    0.82
    beat
    0.81
    headed
    0.81
    bending
    0.80
    Activations Density 0.437%

    No Known Activations