Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11832
    Prev
    Next
    INDEX
    Explanations

    emotional or physical pain related words and expressions

    oai_token-act-pair · gpt-3.5-turbo

    expressions of emotional pain or distress

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DragonMagazine
    -0.82
     Collider
    -0.75
    pires
    -0.69
    idian
    -0.65
     Underground
    -0.64
    ullivan
    -0.64
     SetTextColor
    -0.62
    clerosis
    -0.60
    POL
    -0.58
    iasco
    -0.58
    POSITIVE LOGITS
    ful
    1.43
    fully
    1.19
    lessly
    1.18
     feelings
    1.12
    onies
    1.04
    staking
    0.97
    ted
    0.89
    fulness
    0.87
    les
    0.84
    ling
    0.81
    Activations Density 0.065%

    No Known Activations