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. 11-RES-JB
    6. 19810
    Prev
    Next
    INDEX
    Explanations

    prepositions and words related to comparison or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    phrases that critique social and political issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enium
    -0.86
    ESE
    -0.83
    ©¶æ¥µ
    -0.82
    english
    -0.79
    DragonMagazine
    -0.74
    encia
    -0.74
    hene
    -0.73
     Ank
    -0.73
    istar
    -0.70
    PLA
    -0.67
    POSITIVE LOGITS
     inconvenient
    1.19
     injust
    1.14
     truths
    1.09
     broader
    1.07
     simplistic
    1.07
     trivial
    1.06
     realities
    1.05
     nuance
    1.05
     mundane
    1.04
     unintended
    1.04
    Activations Density 0.471%

    No Known Activations