© 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. 2-RES-JB
    11. 11111
    Prev
    Next
    INDEX
    Explanations

    terms related to a specific topic, potentially related to entertainment or technology

    oai_token-act-pair · gpt-3.5-turbo

    references to puppets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     faint
    -0.74
    ãĥīãĥ©ãĤ´ãĥ³
    -0.70
    76561
    -0.69
    binding
    -0.68
     contempt
    -0.68
     willful
    -0.64
     dissolution
    -0.63
     mesmer
    -0.63
    Textures
    -0.62
     blot
    -0.62
    POSITIVE LOGITS
    enhagen
    1.15
    olicy
    1.11
    upp
    1.10
    ortun
    1.09
    sburgh
    1.04
    enthal
    0.98
    esy
    0.97
    etry
    0.94
    orts
    0.92
    ete
    0.91
    Activations Density 0.004%

    No Known Activations