© 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. 14092
    Prev
    Next
    INDEX
    Explanations

    phrases indicating the beginning or initiation of a process

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to initiating actions or processes

    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
    quickShipAvailable
    -0.76
    uries
    -0.75
    acies
    -0.64
    obi
    -0.62
    atures
    -0.62
    umerous
    -0.62
    istically
    -0.61
    phy
    -0.61
    urnal
    -0.61
    ATHER
    -0.60
    POSITIVE LOGITS
     exploring
    1.01
     mapping
    0.93
     practicing
    0.91
     preparing
    0.91
     applying
    0.90
     cultivating
    0.90
     understanding
    0.88
     figuring
    0.87
     typing
    0.87
     navigating
    0.87
    Activations Density 0.056%

    No Known Activations