© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 24301
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic fields and expertise

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to academic expertise and specialization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ":[
    -1.05
    ↵Âł
    -0.68
     Featuring
    -0.67
    Scroll
    -0.66
    Name
    -0.66
    RAY
    -0.66
    Firstly
    -0.65
    riber
    -0.65
    OUR
    -0.65
    Again
    -0.65
    POSITIVE LOGITS
     extremism
    0.87
     behalf
    0.84
     counterterrorism
    0.83
     insurg
    0.82
     telecommunications
    0.81
     trends
    0.81
    corruption
    0.80
     politics
    0.80
    global
    0.80
     cryptocurrencies
    0.79
    Activations Density 0.190%

    No Known Activations