© 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. 0-RES-JB
    11. 22643
    Prev
    Next
    INDEX
    Explanations

    words related to having a strong interest or enthusiasm for something

    oai_token-act-pair · gpt-3.5-turbo

    expressions of strong interest or enthusiasm

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Andersen
    -0.70
    elle
    -0.69
    ___
    -0.68
    Stat
    -0.67
    colored
    -0.67
    Sequ
    -0.67
    Angel
    -0.65
    atown
    -0.65
     Title
    -0.65
    abo
    -0.65
    POSITIVE LOGITS
     keen
    3.41
     eager
    1.67
     avid
    1.35
     scept
    1.33
     wary
    1.32
     interested
    1.27
     fascinated
    1.27
     delighted
    1.24
     fond
    1.22
     adamant
    1.21
    Activations Density 0.012%

    No Known Activations