© 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. 3108
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters or conflicts

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and formatting symbols

    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
     booking
    -0.73
     trapping
    -0.72
     credentials
    -0.71
     isot
    -0.71
     snowball
    -0.70
     enrollment
    -0.68
     garrison
    -0.68
     miniature
    -0.67
     scheduling
    -0.67
     preservation
    -0.67
    POSITIVE LOGITS
    <|endoftext|>
    1.20
    ↵↵
    1.06
     Anyway
    1.01
    ↵
    0.98
     ********************************
    0.94
     Originally
    0.93
    ↵Âł
    0.90
    ONSORED
    0.90
    ||||
    0.89
     <!--
    0.86
    Activations Density 0.089%

    No Known Activations