© 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. 9-RES-JB
    11. 13463
    Prev
    Next
    INDEX
    Explanations

    phrases encompassing societal issues or discussions about political beliefs and actions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of individuals or groups in the context of gender-related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    yz
    -0.69
    ozy
    -0.68
     Osc
    -0.62
     Rhodes
    -0.62
     Sussex
    -0.60
    eur
    -0.60
     runoff
    -0.57
     Marshal
    -0.56
     Pwr
    -0.56
    çĭ
    -0.56
    POSITIVE LOGITS
    selves
    1.10
    atisf
    1.06
    avior
    1.01
    ername
    0.95
    aviour
    0.91
    aints
    0.89
    lightly
    0.88
    pite
    0.82
    aying
    0.81
    elf
    0.81
    Activations Density 0.141%

    No Known Activations