© 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. 7838
    Prev
    Next
    INDEX
    Explanations

    words related to consequences, ramifications, or repercussions of different events or actions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the outcomes and effects of various events or actions

    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
    swick
    -0.74
    MQ
    -0.74
    AKING
    -0.69
    iverpool
    -0.66
    ÃŁ
    -0.65
    BLIC
    -0.65
    bor
    -0.65
    inately
    -0.65
    atown
    -0.64
    ramid
    -0.64
    POSITIVE LOGITS
     thereof
    1.13
     consequences
    1.04
     repercussions
    0.94
     ramifications
    0.93
     arising
    0.91
     reverber
    0.90
     fallout
    0.89
     implications
    0.84
     for
    0.83
     consequential
    0.81
    Activations Density 0.093%

    No Known Activations