© 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. 9-RES-JB
    11. 14244
    Prev
    Next
    INDEX
    Explanations

    mentions of specific universities, particularly Berkeley

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "Berkeley."

    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
    irt
    -0.72
    meaning
    -0.70
    ivably
    -0.70
    title
    -0.70
    ACTED
    -0.68
    oire
    -0.68
    itimate
    -0.66
    į
    -0.65
    tml
    -0.65
    orship
    -0.64
    POSITIVE LOGITS
    keley
    1.16
     Berkeley
    0.95
    shire
    0.85
     Unified
    0.84
     Heights
    0.82
     Extension
    0.81
     Lab
    0.79
     campus
    0.76
     College
    0.75
     Marina
    0.70
    Activations Density 0.039%

    No Known Activations