© 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. 2-RES-JB
    11. 3958
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "corporal"

    oai_token-act-pair · gpt-3.5-turbo

    references to corporate-related topics and terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IELD
    -0.93
    lihood
    -0.87
    IRO
    -0.85
    joy
    -0.78
    âĻ¥
    -0.78
    WAYS
    -0.75
    WATCH
    -0.75
     Sandwich
    -0.74
     Hale
    -0.73
    cook
    -0.71
    POSITIVE LOGITS
    ates
    1.13
    als
    1.08
    acies
    1.06
    ational
    1.02
    ally
    1.02
    abulary
    1.00
    ating
    0.99
    atum
    0.97
    atem
    0.96
    archs
    0.94
    Activations Density 0.019%

    No Known Activations