© 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. 0-RES-JB
    11. 6771
    Prev
    Next
    INDEX
    Explanations

    chemical compounds related to circles or circular structures

    oai_token-act-pair · gpt-3.5-turbo

    references to motorcycles and cycling concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Shu
    -0.78
     Speak
    -0.66
     Entertainment
    -0.65
     Advance
    -0.65
     hide
    -0.64
     GAME
    -0.63
     secure
    -0.62
     eve
    -0.62
     screen
    -0.62
     UA
    -0.62
    POSITIVE LOGITS
    cycl
    4.73
    cycle
    1.81
     cycl
    1.74
    cyclop
    1.68
     Cycl
    1.61
    cycles
    1.58
     bicycl
    1.33
    Cy
    1.21
    cyl
    1.18
    bike
    1.18
    Activations Density 0.025%

    No Known Activations