© 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. 15526
    Prev
    Next
    INDEX
    Explanations

    first-person singular pronouns and verbs

    oai_token-act-pair · gpt-3.5-turbo

    expressions of regret or self-reflection

    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
    ewitness
    -0.64
     repud
    -0.60
    ceivable
    -0.59
     pastoral
    -0.58
     pestic
    -0.58
     stewards
    -0.57
     corros
    -0.57
     Accessed
    -0.57
     credential
    -0.57
    valued
    -0.57
    POSITIVE LOGITS
     haha
    1.01
    Anyway
    0.98
    laughs
    0.92
     kinda
    0.92
    yeah
    0.89
     :(
    0.88
     anyways
    0.86
     ya
    0.85
     XD
    0.82
    OIL
    0.80
    Activations Density 0.828%

    No Known Activations