© 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. 3-RES-JB
    11. 14776
    Prev
    Next
    INDEX
    Explanations

    words related to strong emotions or intense actions expressed intensively

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to subjectivity and judgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.83
     cryst
    -0.78
    inventoryQuantity
    -0.76
    ItemThumbnailImage
    -0.75
    Ô
    -0.75
    MpServer
    -0.74
     exha
    -0.73
    natureconservancy
    -0.71
    aez
    -0.68
    ¯¯¯¯¯¯¯¯
    -0.68
    POSITIVE LOGITS
    ures
    1.04
    ure
    0.94
    ions
    0.91
    urous
    0.90
    ives
    0.86
    itude
    0.83
    utions
    0.81
    culosis
    0.81
    ution
    0.80
    ject
    0.78
    Activations Density 0.012%

    No Known Activations