© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 12693
    Prev
    Next
    INDEX
    Explanations

    locations, especially cities or landmarks around the world

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and cultural references

    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
    consumer
    -0.92
     blocker
    -0.82
    GOP
    -0.81
     disability
    -0.81
     cryptocurrency
    -0.79
    iculty
    -0.77
     cybersecurity
    -0.77
    Consumer
    -0.77
    direction
    -0.77
    INESS
    -0.76
    POSITIVE LOGITS
     Bombay
    1.13
     Salam
    1.11
     Verd
    1.11
     Sard
    1.08
     Angola
    1.08
     Gibraltar
    1.07
     Baal
    1.07
     Marse
    1.04
     Ves
    1.04
     Scy
    1.04
    Activations Density 0.554%

    No Known Activations