© 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. 4-RES-JB
    11. 17213
    Prev
    Next
    INDEX
    Explanations

    topics related to governmental policies and actions

    oai_token-act-pair · gpt-3.5-turbo

    topics related to social and economic issues, specifically those involving regulations and welfare benefits

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

    No Comments

    Negative Logits
    Õ
    -0.75
    ITNESS
    -0.74
    POSE
    -0.67
    姫
    -0.67
    ?????-
    -0.65
    USER
    -0.64
    ARR
    -0.62
    APTER
    -0.61
    yss
    -0.61
    ãĥ´
    -0.61
    POSITIVE LOGITS
    hops
    0.94
    afety
    0.92
    hips
    0.85
    etting
    0.82
    ynthesis
    0.81
    hip
    0.81
    ometimes
    0.74
    wana
    0.70
    chool
    0.70
    ensitive
    0.69
    Activations Density 0.678%

    No Known Activations