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. 8-RES-JB
    6. 15721
    Prev
    Next
    INDEX
    Explanations

    images or videos that were taken or shot by a specific group or individual

    oai_token-act-pair · gpt-3.5-turbo

    instances of imagery or photographs related to events or observations

    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
    Trade
    -0.80
    redo
    -0.79
    tier
    -0.76
    Market
    -0.74
    itol
    -0.72
     inheritance
    -0.69
     inherit
    -0.69
    ido
    -0.68
     greedy
    -0.68
     unfairly
    -0.66
    POSITIVE LOGITS
     microphones
    1.12
     webcam
    1.12
     GoPro
    1.09
     camera
    1.08
     cameras
    1.07
     infrared
    1.05
     photograp
    1.03
     filming
    1.01
     Camer
    0.98
    camera
    0.97
    Activations Density 0.470%

    No Known Activations