© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 22287
    Prev
    Next
    INDEX
    Explanations

    words ending in "-ish" that describe a quality or characteristic

    oai_token-act-pair · gpt-3.5-turbo

    words that end with the suffix "ish"

    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
     CODE
    -0.62
     STAT
    -0.61
    STAT
    -0.59
     OFFIC
    -0.58
     recognizing
    -0.58
     NULL
    -0.58
     transporting
    -0.57
     Pep
    -0.56
     logger
    -0.56
    assetsadobe
    -0.55
    POSITIVE LOGITS
    ish
    4.45
    ishly
    2.97
    ISH
    2.71
    ishes
    2.69
    ished
    2.47
    ishing
    2.32
    ishment
    2.16
    isher
    1.81
    ishers
    1.72
    ishy
    1.71
    Activations Density 0.018%

    No Known Activations