© 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. 5020
    Prev
    Next
    INDEX
    Explanations

    phrases related to standing out or being unique

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "stand out."

    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
    elf
    -0.94
     confir
    -0.75
    ynchron
    -0.67
    ternal
    -0.66
     lockout
    -0.64
    itamin
    -0.64
     grieving
    -0.63
    ritical
    -0.63
    onds
    -0.63
    ummer
    -0.62
    POSITIVE LOGITS
     amongst
    1.06
    ocl
    0.90
     among
    0.89
    lights
    0.81
     prominently
    0.78
    box
    0.74
    ingly
    0.73
     Flavoring
    0.72
     performers
    0.72
     conspic
    0.71
    Activations Density 0.028%

    No Known Activations