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. 11-RES-JB
    6. 24374
    Prev
    Next
    INDEX
    Explanations

    statements emphasizing the importance of safety and security as top priorities

    oai_token-act-pair · gpt-3.5-turbo

    references to safety and security as top priorities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ago
    -0.73
    enary
    -0.72
     lashes
    -0.64
    bows
    -0.62
    aunder
    -0.62
    stall
    -0.61
    flix
    -0.60
    ãĤº
    -0.59
    igrate
    -0.59
    ops
    -0.58
    POSITIVE LOGITS
     paramount
    1.53
     crucial
    1.22
     critical
    1.14
     key
    1.11
     essential
    1.11
     vital
    1.10
     important
    1.09
     imperative
    1.06
    critical
    1.02
     integral
    1.02
    Activations Density 0.225%

    No Known Activations