Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 2-RES-JB
    6. 10587
    Prev
    Next
    INDEX
    Explanations

    terms related to controversies or scandals, particularly those ending in "-gate."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "gate" and variations of it, indicating a focus on gateways or barriers

    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
     constitu
    -0.67
     subp
    -0.64
     skilled
    -0.63
     pse
    -0.62
    icio
    -0.61
    >>>>>>>>
    -0.60
     servic
    -0.60
    ;;;;;;;;
    -0.59
    aldi
    -0.59
     Adin
    -0.59
    POSITIVE LOGITS
    gate
    1.30
    Gate
    1.11
    way
    0.95
    boro
    0.88
    ways
    0.87
    plot
    0.82
    hammer
    0.82
    ardless
    0.81
    ilee
    0.77
    keepers
    0.77
    Activations Density 0.005%

    No Known Activations