© 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
    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. 14834
    Prev
    Next
    INDEX
    Explanations

    phrases related to abstract concepts or entities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "of."

    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
    CG
    -0.66
    picture
    -0.65
    BILL
    -0.65
    fully
    -0.64
    FN
    -0.64
    Department
    -0.64
    Jr
    -0.62
     resorted
    -0.61
    GU
    -0.61
    anchez
    -0.61
    POSITIVE LOGITS
     Dreams
    1.08
     Excellence
    1.05
     sorts
    0.98
     Souls
    0.98
     Ages
    0.97
     souls
    0.92
    icial
    0.90
     Worlds
    0.89
     Errors
    0.86
     Lies
    0.86
    Activations Density 0.187%

    No Known Activations