© 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. 17625
    Prev
    Next
    INDEX
    Explanations

    verbs related to offering or providing something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "offered" and its variations

    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
    LINE
    -0.70
    igue
    -0.70
    isol
    -0.70
    alde
    -0.68
    psc
    -0.66
    sis
    -0.65
    porter
    -0.64
    suit
    -0.64
    cation
    -0.64
    âĢij
    -0.62
    POSITIVE LOGITS
     condolences
    1.15
     suggestions
    0.91
     refunds
    0.89
     discounts
    0.87
     insight
    0.85
     advice
    0.84
     encouragement
    0.83
     congratulations
    0.78
     assistance
    0.78
     bribes
    0.78
    Activations Density 0.062%

    No Known Activations