© 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. 8-RES-JB
    11. 17069
    Prev
    Next
    INDEX
    Explanations

    instances where the phrase "for one thing" is used in text

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a singular concept or idea, often framed with the phrase "for one thing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Loading
    -0.65
    adr
    -0.64
    Cho
    -0.62
    ãĤ¨ãĥ«
    -0.61
    Textures
    -0.60
    ãĥ¼ãĥĨ
    -0.60
    Deal
    -0.59
    inventoryQuantity
    -0.58
    Bound
    -0.58
    istar
    -0.58
    POSITIVE LOGITS
     sake
    1.11
     reasons
    0.81
     purposes
    0.77
    ummies
    0.70
     reason
    0.68
    enance
    0.64
    abit
    0.63
     Reasons
    0.61
    tarians
    0.60
    plet
    0.60
    Activations Density 0.031%

    No Known Activations