© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 3-RES-JB
    11. 10773
    Prev
    Next
    INDEX
    Explanations

    the name "Gasol" with varying levels of activation

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Gasol in a sports context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ournal
    -0.74
    vironment
    -0.74
     tradem
    -0.72
    etheless
    -0.72
    ¥ŀ
    -0.72
     ende
    -0.69
    avorite
    -0.69
     therap
    -0.67
     bush
    -0.66
    escription
    -0.65
    POSITIVE LOGITS
    oline
    1.30
    Gas
    1.12
     Gas
    0.91
    hib
    0.85
    pora
    0.84
    Plex
    0.82
    gas
    0.81
    olina
    0.77
    Closure
    0.75
     Grenade
    0.75
    Activations Density 0.013%

    No Known Activations