© 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. 6-RES-JB
    11. 937
    Prev
    Next
    INDEX
    Explanations

    phrases related to objects or people being wrapped in something

    oai_token-act-pair · gpt-3.5-turbo

    instances of something being covered or wrapped

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NOW
    -0.76
    TIME
    -0.74
    llor
    -0.73
    URE
    -0.70
    channelAvailability
    -0.68
    SPONSORED
    -0.67
    lihood
    -0.66
    hai
    -0.66
    leans
    -0.66
    lag
    -0.66
    POSITIVE LOGITS
     accordance
    1.04
     lieu
    0.91
     spite
    0.87
     knots
    0.80
    organic
    0.77
    bound
    0.75
     vitro
    0.74
     situ
    0.74
    clusions
    0.74
     essence
    0.74
    Activations Density 0.137%

    No Known Activations