Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 11-RES-JB
    6. 15024
    Prev
    Next
    INDEX
    Explanations

    mentions of polar bears

    oai_token-act-pair · gpt-3.5-turbo

    references to polar bears and the concept of polarization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bler
    -0.77
    rahim
    -0.76
    Es
    -0.71
    edd
    -0.68
    gun
    -0.66
    ree
    -0.65
    ellen
    -0.64
    ei
    -0.62
    edly
    -0.62
    growth
    -0.62
    POSITIVE LOGITS
    izing
    1.25
    ities
    1.13
     vortex
    1.11
     oppos
    1.09
    izer
    1.05
    ising
    1.05
    izers
    1.04
    izations
    1.01
    oid
    1.00
    ised
    1.00
    Activations Density 0.046%

    No Known Activations