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. 9-RES-JB
    6. 7866
    Prev
    Next
    INDEX
    Explanations

    economic and policy-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express skepticism or doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    java
    -0.73
     XXX
    -0.69
    christ
    -0.66
    /?
    -0.64
    hex
    -0.64
    oak
    -0.61
     Inher
    -0.60
    ipation
    -0.60
    upt
    -0.60
    xxxx
    -0.60
    POSITIVE LOGITS
     according
    1.14
     especially
    1.07
     albeit
    1.06
     particularly
    1.05
     undersc
    0.99
    especially
    0.98
     considering
    0.98
     despite
    0.98
     given
    0.94
     prompting
    0.92
    Activations Density 0.310%

    No Known Activations