© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8-RES-JB
    11. 18619
    Prev
    Next
    INDEX
    Explanations

    mentions of the terrorist organization Al-Qaeda

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "Al" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.84
    å£
    -0.72
     Lovecraft
    -0.69
    manship
    -0.67
     sterling
    -0.67
    ãģį
    -0.67
     Vaugh
    -0.63
    åij
    -0.62
    lihood
    -0.61
    ãģ¯
    -0.61
    POSITIVE LOGITS
    manac
    1.26
    gebra
    1.19
    umni
    1.19
    ameda
    1.18
     Jazeera
    1.16
    addin
    1.11
    oha
    1.03
    uminium
    1.02
    gorithm
    1.02
    istar
    0.99
    Activations Density 0.029%

    No Known Activations