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

    Neuronpedia

    APICircuit 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. 7-RES-JB
    6. 9145
    Prev
    Next
    INDEX
    Explanations

    words related to problems, chaos, and negative conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to crises and states of disarray or failure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etch
    -0.72
    origin
    -0.70
    =#
    -0.66
    ather
    -0.62
    ourage
    -0.62
    express
    -0.62
    tein
    -0.62
     eas
    -0.60
    tains
    -0.60
    expression
    -0.60
    POSITIVE LOGITS
     miser
    0.98
     financially
    0.87
    luster
    0.74
    udget
    0.73
     inept
    0.72
    budget
    0.72
     incompetent
    0.70
     incompet
    0.70
     rotten
    0.70
     dysfunction
    0.70
    Activations Density 0.455%

    No Known Activations