© 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. 4-RES-JB
    11. 2924
    Prev
    Next
    INDEX
    Explanations

    instances of the word "hole."

    oai_token-act-pair · gpt-3.5-turbo

    the word "hole" and its variations in various contexts

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

    No Comments

    Negative Logits
    cia
    -0.72
     livest
    -0.67
    uscript
    -0.67
    ority
    -0.65
     Idle
    -0.65
    ullivan
    -0.63
    vez
    -0.62
    IGH
    -0.62
    Bal
    -0.62
    NetMessage
    -0.62
    POSITIVE LOGITS
     hole
    1.26
     Hole
    1.22
     holes
    1.20
    hole
    1.15
    holes
    0.95
     drilled
    0.95
    izons
    0.90
     dug
    0.86
    pots
    0.83
     punched
    0.82
    Activations Density 0.020%

    No Known Activations