© 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. 7819
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate recent actions or creations

    oai_token-act-pair · gpt-3.5-turbo

    instances of the verb "have" and its variations, indicating possession or inclusion

    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
    fail
    -0.75
    apo
    -0.74
    abuse
    -0.72
     Cannot
    -0.71
     srfAttach
    -0.67
    itters
    -0.67
    eem
    -0.65
    ails
    -0.65
    lies
    -0.63
    Reading
    -0.62
    POSITIVE LOGITS
     begun
    1.37
     teamed
    1.35
     chosen
    1.27
     devised
    1.27
     created
    1.23
     been
    1.23
     assembled
    1.22
     partnered
    1.22
     gotten
    1.21
     collaborated
    1.18
    Activations Density 0.278%

    No Known Activations