© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    11. 5091
    Prev
    Next
    INDEX
    Explanations

    phrases related to positioning or distancing

    oai_token-act-pair · gpt-3.5-turbo

    reflexive pronouns used to indicate identity or representation

    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
     understatement
    -0.69
    WORK
    -0.67
    our
    -0.60
     grade
    -0.59
    onal
    -0.58
    emis
    -0.58
     Whis
    -0.57
     violation
    -0.57
    origin
    -0.56
    nic
    -0.56
    POSITIVE LOGITS
    é¾įå¥ij士
    0.81
    é¾įåĸļ士
    0.78
     territ
    0.76
     creatively
    0.76
    selves
    0.73
    姫
    0.72
    DragonMagazine
    0.72
    åĤ
    0.70
    acl
    0.70
     captcha
    0.70
    Activations Density 0.049%

    No Known Activations