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. 7-RES-JB
    6. 5573
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict or controversy

    oai_token-act-pair · gpt-3.5-turbo

    metaphorical expressions related to conflict or challenges

    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
     Household
    -0.63
     Supplement
    -0.62
     inspect
    -0.58
     TBA
    -0.57
     Equipment
    -0.55
     Entry
    -0.54
     inspected
    -0.54
     manned
    -0.54
    anut
    -0.53
     towed
    -0.53
    POSITIVE LOGITS
     cynicism
    0.93
     semantic
    0.89
     fallacy
    0.88
     doubt
    0.82
     rhetorical
    0.80
     assumption
    0.79
     skepticism
    0.79
     irony
    0.79
     hypocrisy
    0.78
     delusions
    0.77
    Activations Density 0.969%

    No Known Activations