© 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. 10-RES-JB
    11. 11042
    Prev
    Next
    INDEX
    Explanations

    names related to the surname "Kiran"

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Kirchner."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     comma
    -0.65
     Centauri
    -0.60
     Signal
    -0.59
    ured
    -0.59
    ered
    -0.59
     dividing
    -0.58
     Thirty
    -0.58
    urer
    -0.58
    herty
    -0.56
     Spread
    -0.56
    POSITIVE LOGITS
    bys
    1.08
    wan
    1.00
    ten
    0.99
    yu
    0.98
    ky
    0.95
    ihara
    0.92
    lington
    0.91
    sch
    0.91
    kat
    0.90
    ansas
    0.88
    Activations Density 0.021%

    No Known Activations