© 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. 10-RES-JB
    11. 10537
    Prev
    Next
    INDEX
    Explanations

    contractions with 's

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "it’s" in various contexts

    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
    nel
    -0.78
    DS
    -0.73
    ESE
    -0.72
    %%
    -0.70
    ievers
    -0.70
    igraph
    -0.69
    roit
    -0.68
    soever
    -0.67
    ollow
    -0.67
    INST
    -0.66
    POSITIVE LOGITS
     been
    1.39
     gotta
    1.32
     gotten
    1.21
     got
    1.14
     gonna
    1.11
     unclear
    1.08
    been
    1.02
     doubtful
    0.98
     conceivable
    0.97
     impossible
    0.97
    Activations Density 0.121%

    No Known Activations