© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 11361
    Prev
    Next
    INDEX
    Explanations

    words related to generating something, such as power, revenue, and profits

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of generating

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bull
    -0.75
     TAMADRA
    -0.73
     Velvet
    -0.73
    glass
    -0.73
    tta
    -0.69
     Jess
    -0.69
    fell
    -0.67
    aby
    -0.65
     Sharon
    -0.63
     Hastings
    -0.63
    POSITIVE LOGITS
     generate
    3.20
     generates
    2.44
     generating
    2.31
     generated
    2.28
    generated
    1.86
     Gener
    1.62
     generator
    1.62
     generators
    1.60
    Gener
    1.58
     derive
    1.55
    Activations Density 0.022%

    No Known Activations