© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 2734
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, specifically those containing the letters "ks"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ks"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mosqu
    -0.76
    Ø©
    -0.70
    ب
    -0.69
    Interstitial
    -0.69
    ä¸ī
    -0.67
    اØ
    -0.67
    ت
    -0.66
    ÙĦ
    -0.65
     Malf
    -0.62
    ANN
    -0.61
    POSITIVE LOGITS
    crew
    1.38
    creen
    1.38
    wagen
    1.24
    haw
    1.22
    ilver
    1.10
    cape
    1.06
    hiro
    1.06
    andr
    1.05
    hire
    1.01
    ansas
    1.00
    Activations Density 0.041%

    No Known Activations