© 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. 10-RES-JB
    11. 17307
    Prev
    Next
    INDEX
    Explanations

    phrases containing connected ideas or concepts

    oai_token-act-pair · gpt-3.5-turbo

    words or phrases that occur frequently in contexts related to political discussions

    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
    "],
    -0.64
    vec
    -0.62
    Ping
    -0.61
    olves
    -0.60
    FREE
    -0.59
    BU
    -0.59
    Alert
    -0.57
    icter
    -0.56
    hart
    -0.54
    bug
    -0.54
    POSITIVE LOGITS
     indeed
    1.44
     especially
    1.44
     preferably
    1.36
     particularly
    1.34
     consequently
    1.33
     therefore
    1.28
    especially
    1.28
     hence
    1.25
     furthermore
    1.21
     moreover
    1.19
    Activations Density 0.121%

    No Known Activations