© 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. 5448
    Prev
    Next
    INDEX
    Explanations

    phrases related to achievements or accomplishments

    oai_token-act-pair · gpt-3.5-turbo

    periods and other punctuation that indicate sentence boundaries

    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
     ogre
    -0.62
     committee
    -0.62
     patri
    -0.62
     correction
    -0.61
     cabbage
    -0.60
     yourselves
    -0.59
     optional
    -0.59
     propri
    -0.59
     congress
    -0.58
     marketplace
    -0.58
    POSITIVE LOGITS
    Born
    1.43
     Born
    1.23
    His
    1.16
    Laun
    1.07
    Known
    1.05
    Speaking
    1.02
     His
    0.97
    He
    0.96
     Having
    0.94
     Inspired
    0.93
    Activations Density 0.419%

    No Known Activations