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. 11-RES-JB
    6. 8916
    Prev
    Next
    INDEX
    Explanations

    phrases related to high energy or high profile events or situations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to "high" intensity or profile qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hasan
    -0.65
    uers
    -0.65
    uphem
    -0.63
    thening
    -0.60
    iling
    -0.60
    orers
    -0.60
     UNITED
    -0.60
     Till
    -0.59
    iliation
    -0.59
     merged
    -0.58
    POSITIVE LOGITS
    brow
    1.19
    fal
    1.13
    profile
    1.03
     profile
    0.96
    stakes
    0.95
     stakes
    0.91
    handed
    0.91
     caliber
    0.90
    flying
    0.89
    lights
    0.87
    Activations Density 0.077%

    No Known Activations