© 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. 11-RES-JB
    11. 18500
    Prev
    Next
    INDEX
    Explanations

    phrases indicating continuing or transitioning to further discussion

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "went on" followed by actions or explanations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipop
    -0.75
    ãĤ£
    -0.70
    selves
    -0.69
     Shards
    -0.67
    uko
    -0.63
    assets
    -0.63
    ahu
    -0.61
    Ïģ
    -0.61
    wcsstore
    -0.60
    2019
    -0.60
    POSITIVE LOGITS
     record
    0.77
     to
    0.75
     tir
    0.75
     offense
    0.74
     hiatus
    0.72
     rant
    0.70
     reiterate
    0.68
     recount
    0.66
     stride
    0.65
     sarcast
    0.65
    Activations Density 0.015%

    No Known Activations