© 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. 10-RES-JB
    11. 20215
    Prev
    Next
    INDEX
    Explanations

    keywords related to business deals, agreements, and approvals

    oai_token-act-pair · gpt-3.5-turbo

    references to legal or regulatory actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.79
     portraits
    -0.74
    Tips
    -0.71
     Droid
    -0.70
     Doodle
    -0.69
    ktop
    -0.69
     reminding
    -0.68
    ĸļ
    -0.67
     impressions
    -0.65
     Decoder
    -0.64
    POSITIVE LOGITS
     proceed
    1.09
     succeed
    1.09
     fruition
    1.00
     stalled
    0.99
     derailed
    0.97
     shel
    0.96
     approved
    0.94
     defund
    0.93
    pleted
    0.92
     scrapped
    0.92
    Activations Density 0.374%

    No Known Activations