© 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. 1-RES-JB
    11. 3339
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to something being acceptable or not

    oai_token-act-pair · gpt-3.5-turbo

    concepts of acceptability and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hunt
    -0.82
    berry
    -0.80
    king
    -0.79
    dream
    -0.78
    hunter
    -0.76
    wan
    -0.74
    set
    -0.73
    hung
    -0.73
    GPU
    -0.72
    older
    -0.72
    POSITIVE LOGITS
     acceptable
    1.04
     agre
    1.00
     undermin
    0.82
    soDeliveryDate
    0.81
     compromises
    0.81
    lihood
    0.81
     mosqu
    0.80
     srfAttach
    0.79
    ible
    0.78
    GoldMagikarp
    0.78
    Activations Density 0.007%

    No Known Activations