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

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 20713
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases starting with "of" followed by a noun phrase

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "much of" in relation to various topics

    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
    cards
    -0.89
    aughters
    -0.83
    chairs
    -0.77
     Cosponsors
    -0.77
     cleaners
    -0.76
    rants
    -0.76
    =]
    -0.75
     dstg
    -0.71
    ples
    -0.71
    ares
    -0.71
    POSITIVE LOGITS
     southwestern
    0.75
     southeastern
    0.74
     Europe
    0.74
     misinformation
    0.71
     Silicon
    0.69
     Northeast
    0.67
    tering
    0.66
     coastline
    0.65
     southern
    0.65
     northwestern
    0.64
    Activations Density 0.086%

    No Known Activations