© 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. 8-RES-JB
    11. 3093
    Prev
    Next
    INDEX
    Explanations

    keywords related to offerings, restrictions, investments, and advantages in a context that involves systems or industries

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to financial contributions and charitable support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ghazi
    -0.72
     Rodham
    -0.70
     contrace
    -0.66
    Newsletter
    -0.65
     Kissinger
    -0.64
    missible
    -0.63
     Klan
    -0.62
     Hasan
    -0.61
     repe
    -0.61
    annis
    -0.60
    POSITIVE LOGITS
     ;)
    0.87
     haha
    0.79
     :)
    0.78
     ðŁĻĤ
    0.77
    ware
    0.73
     assumption
    0.73
     disclaimer
    0.72
    âķIJâķIJ
    0.72
     Valve
    0.72
     towards
    0.70
    Activations Density 0.795%

    No Known Activations