© 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. 2670
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning dates or time periods

    oai_token-act-pair · gpt-3.5-turbo

    references to significant events or trends impacting people

    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
     risked
    -0.79
     ][
    -0.65
     ¶
    -0.60
    ¶
    -0.60
     infiltrated
    -0.57
     ÂŃ
    -0.56
     Holocaust
    -0.55
     Nazis
    -0.55
     Nazi
    -0.54
     ])
    -0.54
    POSITIVE LOGITS
    OIL
    0.68
    oother
    0.67
    erenn
    0.64
    emi
    0.64
    assic
    0.62
    enium
    0.59
     2019
    0.59
     rematch
    0.59
    bye
    0.59
    ORY
    0.58
    Activations Density 1.560%

    No Known Activations