© 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. 6-RES-JB
    11. 15063
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or consequence

    oai_token-act-pair · gpt-3.5-turbo

    special characters or symbols within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     decomp
    -0.74
     scatter
    -0.74
     nucleus
    -0.72
     multiplying
    -0.71
     dumps
    -0.70
     buggy
    -0.70
     multiplied
    -0.70
     plain
    -0.69
     minim
    -0.68
     sliding
    -0.67
    POSITIVE LOGITS
    º
    1.17
    £
    1.11
    ¹
    1.10
    ®
    1.04
    »
    1.00
    ĸļ
    0.97
    ¡
    0.96
    Į
    0.96
    ¿
    0.95
    ª
    0.93
    Activations Density 0.146%

    No Known Activations