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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10136
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical violence and destruction

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases related to being "cut off" or "taken away."

    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
    uploads
    -0.79
    ially
    -0.73
    catentry
    -0.71
    SPONSORED
    -0.69
    specified
    -0.68
     pertaining
    -0.67
    ivities
    -0.67
     Emerging
    -0.66
    IAS
    -0.65
    MN
    -0.65
    POSITIVE LOGITS
     cages
    0.81
     onto
    0.79
     barric
    0.78
     flats
    0.77
     broom
    0.71
     blankets
    0.71
     toilets
    0.70
     carts
    0.68
     ponds
    0.68
     nests
    0.67
    Activations Density 1.363%

    No Known Activations