© 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. 8-RES-JB
    6. 23494
    Prev
    Next
    INDEX
    Explanations

    specific events or occasions

    oai_token-act-pair · gpt-3.5-turbo

    references to educational content and institutions

    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
     awa
    -0.65
    inventoryQuantity
    -0.64
     seiz
    -0.61
     bloom
    -0.60
    =$
    -0.57
    )=
    -0.57
    aeper
    -0.56
     SERV
    -0.56
     morphed
    -0.55
     defective
    -0.55
    POSITIVE LOGITS
     Awards
    0.81
     Podcast
    0.79
     Insight
    0.76
     Analysis
    0.72
     newsletter
    0.71
     podcast
    0.70
     Journalism
    0.70
     ].
    0.69
     Strategies
    0.68
     Reporter
    0.68
    Activations Density 0.430%

    No Known Activations