© 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. 386
    Prev
    Next
    INDEX
    Explanations

    words related to digging or excavation

    oai_token-act-pair · gpt-3.5-turbo

    the word "bur" 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
    éĹĺ
    -0.80
     Nanto
    -0.74
    FTWARE
    -0.74
    é¾įå
    -0.74
    aunder
    -0.73
    姫
    -0.70
    )=(
    -0.69
    externalActionCode
    -0.69
     SYSTEM
    -0.68
     Directive
    -0.68
    POSITIVE LOGITS
    rito
    1.24
    rows
    1.20
    rowing
    1.18
    row
    1.06
     bur
    1.06
    pee
    0.99
    rit
    0.99
    pees
    0.98
    gey
    0.97
    geons
    0.96
    Activations Density 0.004%

    No Known Activations