© 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. 3639
    Prev
    Next
    INDEX
    Explanations

    words related to specific technical details, such as product names or dates

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of a specific pattern or placeholder indicating a break in the document

    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
    hazard
    -0.28
    sic
    -0.27
     blah
    -0.27
     disadvant
    -0.26
    existent
    -0.26
    ĪĴ
    -0.25
     outweigh
    -0.25
    eday
    -0.25
     guiActiveUnfocused
    -0.25
     requisite
    -0.25
    POSITIVE LOGITS
     ..........
    0.29
    ¶
    0.27
     âĢº
    0.27
     Background
    0.26
     Donald
    0.25
    )--
    0.24
     Hero
    0.23
     Hillary
    0.23
     Profile
    0.23
    oÄŁan
    0.23
    Activations Density 5.537%

    No Known Activations