© 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. 6209
    Prev
    Next
    INDEX
    Explanations

    scheduled events and timings

    oai_token-act-pair · gpt-3.5-turbo

    references to scheduled events and important dates

    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
    Reviewer
    -0.94
     temptation
    -0.79
    mob
    -0.78
     barriers
    -0.78
    aughs
    -0.74
     Flavoring
    -0.69
     reintrodu
    -0.68
    arsh
    -0.68
     contag
    -0.68
    ustration
    -0.67
    POSITIVE LOGITS
     located
    0.86
     ZIP
    0.81
     AMERICA
    0.79
    REDACTED
    0.79
     spelled
    0.79
     nort
    0.78
     Located
    0.76
     1941
    0.75
     LOC
    0.74
     1898
    0.74
    Activations Density 0.918%

    No Known Activations