© 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. 2-RES-JB
    11. 3884
    Prev
    Next
    INDEX
    Explanations

    sensitive information related to well-known terrorism groups and individuals

    oai_token-act-pair · gpt-3.5-turbo

    names of individuals associated with specific groups or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Uncharted
    -0.80
    wcs
    -0.79
     Goose
    -0.77
     Wally
    -0.75
     Voy
    -0.74
     Blizz
    -0.74
     Pixar
    -0.73
     Turing
    -0.72
     Pyth
    -0.72
     Curiosity
    -0.71
    POSITIVE LOGITS
    iyah
    1.19
    abi
    1.19
     Hussein
    1.05
     Ahmad
    1.04
    ifa
    1.01
     Mahm
    1.00
     jihadist
    1.00
    abad
    1.00
    uala
    0.99
    awi
    0.99
    Activations Density 0.395%

    No Known Activations