© 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. 10-RES-JB
    11. 10774
    Prev
    Next
    INDEX
    Explanations

    phrases related to excitement and anticipation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of excitement and interest in new systems, technologies, or initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fuck
    -0.76
    wrong
    -0.75
    ERROR
    -0.71
    nery
    -0.71
     sinners
    -0.71
    Damage
    -0.71
    Cause
    -0.69
    gencies
    -0.69
    Viol
    -0.68
    Jews
    -0.68
    POSITIVE LOGITS
     blockchain
    1.12
     integrating
    1.07
     improved
    1.02
     wearable
    1.00
     automation
    0.99
     implementing
    0.97
     cryptocurrencies
    0.97
     expanding
    0.97
     innovation
    0.97
     improving
    0.96
    Activations Density 0.467%

    No Known Activations