© 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. 10473
    Prev
    Next
    INDEX
    Explanations

    various contexts in which a desire or need is met

    oai_token-act-pair · gpt-3.5-turbo

    expressions indicating the fulfillment of needs or desires

    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
    olan
    -0.74
     Mehran
    -0.73
     Honour
    -0.71
     prone
    -0.69
     constructed
    -0.64
    Downloadha
    -0.64
    destruct
    -0.61
     Osc
    -0.60
    clips
    -0.58
    ever
    -0.57
    POSITIVE LOGITS
    ments
    1.08
    MENTS
    0.96
     satisfy
    0.94
    ¿½
    0.93
    âķIJâķIJ
    0.93
    ysis
    0.90
    imaru
    0.88
    ingly
    0.83
     satisf
    0.81
     appease
    0.77
    Activations Density 0.017%

    No Known Activations