© 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. 7-RES-JB
    11. 23758
    Prev
    Next
    INDEX
    Explanations

    words related to making appeals or requests

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making requests or appeals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Berk
    -0.72
    furt
    -0.70
    stadt
    -0.70
     Dill
    -0.65
     Lauder
    -0.65
     Stru
    -0.64
    grown
    -0.59
     Sapp
    -0.59
     ain
    -0.58
     Falk
    -0.58
    POSITIVE LOGITS
     intervene
    0.97
     clarify
    0.91
     reassure
    0.85
     abolish
    0.84
     justify
    0.83
     reconsider
    0.82
    ĸļ
    0.81
     postpone
    0.80
     compel
    0.78
     conserve
    0.78
    Activations Density 0.137%

    No Known Activations