© 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. 1-RES-JB
    11. 965
    Prev
    Next
    INDEX
    Explanations

    mentions of the location "Kh9"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Kh."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĹĺ
    -0.83
    EMENT
    -0.78
    swick
    -0.76
    FOX
    -0.74
    Ted
    -0.69
     Bleach
    -0.68
     sidx
    -0.68
     BART
    -0.67
    Bloom
    -0.67
    âĸ¬âĸ¬
    -0.67
    POSITIVE LOGITS
    aji
    1.12
     Kh
    1.08
    Kh
    0.93
    izoph
    0.86
    oub
    0.84
    osh
    0.81
    ohan
    0.80
     kh
    0.80
    istani
    0.79
    orn
    0.79
    Activations Density 0.006%

    No Known Activations