© 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. 2-RES-JB
    11. 881
    Prev
    Next
    INDEX
    Explanations

    the word "holes"

    oai_token-act-pair · gpt-4-turbo

    references to physical holes in objects or structures

    oai_token-act-pair · gpt-3.5-turbo

    references to "holes" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Motion
    -0.80
    ãĥ£
    -0.66
    Bal
    -0.64
    Revolution
    -0.64
     ALS
    -0.63
    >>>>>>>>
    -0.63
     forestry
    -0.62
    NOR
    -0.62
     EMS
    -0.62
    USA
    -0.59
    POSITIVE LOGITS
    pots
    1.54
    poons
    1.29
    ettings
    1.16
     holes
    1.16
    mith
    1.14
    hooting
    1.09
    paces
    1.09
    etting
    1.09
    hips
    1.08
    creen
    1.07
    Activations Density 0.024%

    No Known Activations