© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22730
    Prev
    Next
    INDEX
    Explanations

    references to events or concepts from the past

    oai_token-act-pair · gpt-3.5-turbo

    references to past events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deregulation
    -0.78
     bree
    -0.69
     automation
    -0.68
    SY
    -0.67
     yuan
    -0.66
     cruiser
    -0.63
     linkage
    -0.63
     operation
    -0.62
     fiercely
    -0.62
    é¾įåĸļ士
    -0.61
    POSITIVE LOGITS
     Past
    3.56
    Past
    2.46
    past
    1.91
     Present
    1.27
     Pastor
    1.21
     Future
    1.08
     Innocent
    1.07
     pasta
    1.07
     Parish
    1.06
     Painter
    0.97
    Activations Density 0.025%

    No Known Activations