© 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. 16475
    Prev
    Next
    INDEX
    Explanations

    names or references to specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    the name "Al" as part of various personal names and affiliations

    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
    EEE
    -0.81
    ELL
    -0.65
    eon
    -0.64
    ALLY
    -0.63
     sterling
    -0.62
     Twain
    -0.61
    uncture
    -0.58
     scraping
    -0.58
     vagina
    -0.57
    herical
    -0.56
    POSITIVE LOGITS
     Qaeda
    1.15
     Assad
    0.99
     Baghd
    0.99
     Jazeera
    0.99
    ibaba
    0.97
    Assad
    0.96
     Abbas
    0.95
     Hussein
    0.95
    ayn
    0.94
     Hassan
    0.90
    Activations Density 0.026%

    No Known Activations