© 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
    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. 7248
    Prev
    Next
    INDEX
    Explanations

    references to specific cultural or regional markers

    oai_token-act-pair · gpt-3.5-turbo

    specific cultural or ethnic identifiers and descriptors

    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
    anwhile
    -0.85
     MFT
    -0.76
    thens
    -0.73
    ateurs
    -0.72
    ittee
    -0.71
    idates
    -0.67
    brates
    -0.66
    lees
    -0.65
    ittees
    -0.65
     WEEK
    -0.64
    POSITIVE LOGITS
    esque
    1.53
     flair
    1.32
     accents
    1.27
     style
    1.23
     themed
    1.16
     accent
    1.15
     sensibilities
    1.11
     slang
    1.09
    ish
    1.04
     styled
    1.03
    Activations Density 0.423%

    No Known Activations