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. 6-RES-JB
    6. 6180
    Prev
    Next
    INDEX
    Explanations

    words related to expressing worry or apprehension

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "concerns" related to various issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ingers
    -0.78
    ctors
    -0.70
    obos
    -0.69
    obs
    -0.69
    nice
    -0.67
    ortunately
    -0.67
     Carbuncle
    -0.67
     Bom
    -0.67
    oba
    -0.66
     slick
    -0.66
    POSITIVE LOGITS
    wart
    1.02
    warts
    0.98
     trolling
    0.84
     concerns
    0.79
     Concern
    0.78
     concern
    0.78
     regarding
    0.77
     raised
    0.77
     voiced
    0.76
    cern
    0.72
    Activations Density 0.040%

    No Known Activations