© 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. 15014
    Prev
    Next
    INDEX
    Explanations

    Contractions with "doesn't" in the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "doesn't."

    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
     enthusi
    -0.94
    anwhile
    -0.92
     eleph
    -0.91
     pione
    -0.86
    Þ
    -0.84
     newcom
    -0.84
     princ
    -0.82
     exha
    -0.80
    ò
    -0.77
     withd
    -0.76
    POSITIVE LOGITS
    't
    1.91
    ned
    1.00
    itely
    1.00
    ÃŃ
    0.91
    athan
    0.88
    uts
    0.87
    ´
    0.84
    ALD
    0.83
    ates
    0.82
    etsk
    0.81
    Activations Density 0.171%

    No Known Activations