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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 9-RES-JB
    6. 12560
    Prev
    Next
    INDEX
    Explanations

    locations in a city or town

    oai_token-act-pair · gpt-3.5-turbo

    the end-of-document indicator

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     censored
    -0.86
     chore
    -0.82
     worldwide
    -0.81
     hitherto
    -0.80
     authoritarian
    -0.80
     acron
    -0.79
     pse
    -0.79
     voc
    -0.79
     congratulations
    -0.78
    OPLE
    -0.78
    POSITIVE LOGITS
    heny
    1.35
     Creek
    1.29
    esville
    1.28
     Harbor
    1.24
    endale
    1.20
    vale
    1.18
     Avenue
    1.17
    erville
    1.16
     River
    1.14
    inton
    1.11
    Activations Density 0.338%

    No Known Activations