© 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. 9-RES-JB
    11. 15469
    Prev
    Next
    INDEX
    Explanations

    phrases related to instructions or strategies

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing possession or existence

    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
    Synopsis
    -0.76
     ®
    -0.74
     UPDATE
    -0.73
     Updated
    -0.66
    ãĥ«
    -0.65
    christ
    -0.65
     Recall
    -0.65
    assis
    -0.65
    cus
    -0.65
    edition
    -0.64
    POSITIVE LOGITS
     gotta
    1.07
     tremendous
    1.05
     been
    0.97
     gonna
    0.95
     lots
    0.91
     somebody
    0.90
     definitely
    0.90
     unbelievable
    0.84
     tons
    0.84
     plenty
    0.84
    Activations Density 0.269%

    No Known Activations