© 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. 0-RES-JB
    11. 22702
    Prev
    Next
    INDEX
    Explanations

    phrases related to serving or providing for others

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "serve."

    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
    BUG
    -0.68
     Ong
    -0.66
     Rover
    -0.65
     Journals
    -0.63
     Lot
    -0.62
     Bugs
    -0.61
    metic
    -0.60
     Horror
    -0.60
     Bug
    -0.60
     BIT
    -0.58
    POSITIVE LOGITS
     serve
    3.54
     Serve
    2.43
     served
    2.32
     serves
    2.27
     serving
    2.16
     Serving
    1.76
    served
    1.65
    serving
    1.63
     SERV
    1.45
    Serv
    1.42
    Activations Density 0.020%

    No Known Activations