© 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. 642
    Prev
    Next
    INDEX
    Explanations

    phrases related to cleaning or removing unwanted substances

    oai_token-act-pair · gpt-3.5-turbo

    terms related to removal and interaction with media or information

    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
     span
    -0.68
     pitch
    -0.67
     benefit
    -0.67
     continue
    -0.67
     claim
    -0.67
     challenge
    -0.66
     decrease
    -0.66
     snag
    -0.65
     plan
    -0.65
     gain
    -0.65
    POSITIVE LOGITS
     dives
    1.76
     lifts
    1.75
     wipes
    1.75
     feeds
    1.74
     fills
    1.74
     pushes
    1.73
     pulls
    1.73
     rushes
    1.72
     bends
    1.71
     draws
    1.71
    Activations Density 0.155%

    No Known Activations