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. 8-RES-JB
    6. 18400
    Prev
    Next
    INDEX
    Explanations

    phrases related to socio-political issues

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate comparisons and varying levels of quality or experience

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     scrimmage
    -0.77
     calculator
    -0.76
     Calculator
    -0.74
     procedure
    -0.72
     introduction
    -0.72
     Diary
    -0.71
     Conquest
    -0.70
    ilogy
    -0.70
     palette
    -0.69
     Massacre
    -0.69
    POSITIVE LOGITS
    paying
    0.96
    priced
    0.93
    qualified
    0.93
    protected
    0.91
    existing
    0.91
    listed
    0.90
    sized
    0.89
    serving
    0.88
    grown
    0.88
    classified
    0.88
    Activations Density 0.384%

    No Known Activations