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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 9-RES-JB
    11. 3224
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or attributes within a business or organizational context

    oai_token-act-pair · gpt-3.5-turbo

    topics related to diversity, community engagement, and workplace dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Canaver
    -0.90
     Jed
    -0.61
     pity
    -0.60
    alach
    -0.60
     Dems
    -0.60
    trak
    -0.59
     Dunk
    -0.58
     Collider
    -0.57
    REDACTED
    -0.57
    iency
    -0.56
    POSITIVE LOGITS
    .
    0.80
     selves
    0.79
    selves
    0.79
     individually
    0.77
     irrespective
    0.77
     regardless
    0.76
     relative
    0.75
     lest
    0.75
     electronically
    0.73
     accordingly
    0.71
    Activations Density 0.473%

    No Known Activations