© 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. 1-RES-JB
    11. 13405
    Prev
    Next
    INDEX
    Explanations

    words related to football/soccer, such as "goal," "team," or "player."

    oai_token-act-pair · gpt-3.5-turbo

    references to various types of networks or connections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IP
    -0.74
     Ancest
    -0.72
     Borders
    -0.72
     Grave
    -0.71
     Hands
    -0.68
     Minor
    -0.65
     Vet
    -0.64
     Patent
    -0.64
     Tribe
    -0.63
     Plant
    -0.62
    POSITIVE LOGITS
    bol
    0.97
    initions
    0.94
    theless
    0.92
    racuse
    0.90
    nas
    0.86
    elong
    0.86
    ornings
    0.86
    etheless
    0.84
    dule
    0.84
    pins
    0.83
    Activations Density 0.031%

    No Known Activations