© 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. 0-RES-JB
    11. 11504
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to the name "Khalil"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific names, particularly Khal and Raf

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IENCE
    -0.74
    BS
    -0.64
    etting
    -0.64
     testers
    -0.64
     Tacoma
    -0.62
     uptake
    -0.62
     trout
    -0.61
    OPE
    -0.61
     ABS
    -0.61
    otype
    -0.60
    POSITIVE LOGITS
     Khal
    4.35
     Malk
    1.35
     Jal
    1.29
     Mahm
    1.24
     Zah
    1.23
    Kh
    1.19
     Abdul
    1.18
     Kham
    1.17
     Mohamed
    1.16
     Kand
    1.15
    Activations Density 0.014%

    No Known Activations