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

    Neuronpedia

    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. 11-RES-JB
    11. 23272
    Prev
    Next
    INDEX
    Explanations

    verbs indicating speech or communication

    oai_token-act-pair · gpt-3.5-turbo

    quotations and statements related to personal opinions or remarks

    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
     thereafter
    -0.88
    sequently
    -0.80
     analys
    -0.76
     subsequently
    -0.74
    ãĢIJ
    -0.71
     retrospect
    -0.71
     afterwards
    -0.70
     âĢ
    -0.69
     subsequent
    -0.68
    BRE
    -0.68
    POSITIVE LOGITS
     opposes
    0.80
     Supporters
    0.73
     said
    0.73
     oppose
    0.67
    Supporters
    0.65
     says
    0.64
     encourages
    0.63
     owns
    0.63
    hello
    0.62
     welcomes
    0.62
    Activations Density 0.563%

    No Known Activations