© 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. 4-RES-JB
    11. 8539
    Prev
    Next
    INDEX
    Explanations

    names related to specific organizations, locations, or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to institutions, organizations, or entities

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

    No Comments

    Negative Logits
    Ô
    -0.65
    ļé
    -0.61
    ĪĴ
    -0.59
    ãĤ½
    -0.57
    ãĤ¨ãĥ«
    -0.56
    ãĤ¢ãĥ«
    -0.54
    ¶æ
    -0.53
    ¿½
    -0.53
    ãĥīãĥ©
    -0.52
    sbm
    -0.52
    POSITIVE LOGITS
     Museum
    0.51
     Accountability
    0.50
     itself
    0.49
     logo
    0.49
     spotlight
    0.48
    's
    0.48
     entrance
    0.48
     hierarchy
    0.48
    Enlarge
    0.48
    iest
    0.47
    Activations Density 0.987%

    No Known Activations