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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 6128
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences that start with "Having."

    oai_token-act-pair · gpt-3.5-turbo

    the word "Having" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interested
    -0.70
    etting
    -0.68
    etter
    -0.67
     Avalanche
    -0.61
    tel
    -0.61
     Creep
    -0.59
     kicker
    -0.59
    JC
    -0.59
     Via
    -0.57
    VR
    -0.56
    POSITIVE LOGITS
     undergone
    1.21
     been
    1.19
    been
    0.98
     participated
    0.98
     gotten
    0.95
     eaten
    0.94
     listened
    0.93
     collaborated
    0.92
     heard
    0.92
     endured
    0.92
    Activations Density 0.062%

    No Known Activations