© 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. 10-RES-JB
    11. 6615
    Prev
    Next
    INDEX
    Explanations

    words related to official titles or affiliations

    oai_token-act-pair · gpt-3.5-turbo

    instances of acronyms or abbreviations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Magikarp
    -0.62
     Archangel
    -0.60
    headers
    -0.59
     Gun
    -0.59
    frey
    -0.58
     darts
    -0.58
    wings
    -0.57
    SOURCE
    -0.57
     Pearl
    -0.57
    blast
    -0.56
    POSITIVE LOGITS
    cific
    0.98
    pta
    0.83
    ificant
    0.82
    uration
    0.79
    utes
    0.77
    ceed
    0.76
    encies
    0.75
    acist
    0.72
    ribing
    0.72
    ccess
    0.71
    Activations Density 0.061%

    No Known Activations