© 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. 11721
    Prev
    Next
    INDEX
    Explanations

    specific terms related to marking or highlighting, such as "marker," "pointer," or "marker symbolizing."

    oai_token-act-pair · gpt-3.5-turbo

    references to markers and pointers in various contexts

    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
    iated
    -0.91
    erella
    -0.83
    agar
    -0.78
    iencies
    -0.77
    erest
    -0.76
    urer
    -0.76
    nesses
    -0.76
    ynski
    -0.74
    nar
    -0.70
    esm
    -0.70
    POSITIVE LOGITS
     marker
    0.97
     markers
    0.81
    holder
    0.77
     pens
    0.75
    posts
    0.73
    OPLE
    0.71
     Vie
    0.70
     litter
    0.70
    cil
    0.69
     Tec
    0.68
    Activations Density 0.055%

    No Known Activations