© 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. 18466
    Prev
    Next
    INDEX
    Explanations

    adjectives describing characteristics or qualities of people or things

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate significant attributes or qualities of people or entities

    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
     LLC
    -0.68
     Firm
    -0.67
    wark
    -0.64
     Gaia
    -0.62
    Monitor
    -0.62
     Geh
    -0.61
     FIR
    -0.61
     Shay
    -0.61
     Frey
    -0.60
     Gel
    -0.60
    POSITIVE LOGITS
     prowess
    0.99
    itiveness
    0.95
     penchant
    0.91
     antics
    0.91
     propensity
    0.91
     tendency
    0.89
    ability
    0.88
     versatility
    0.88
    lessness
    0.87
     nature
    0.87
    Activations Density 0.360%

    No Known Activations