© 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. 3-RES-JB
    11. 9347
    Prev
    Next
    INDEX
    Explanations

    phrases related to granting permission or approval

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "gave" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Die
    -0.68
    {{
    -0.67
    ansas
    -0.63
    Cache
    -0.62
    Sphere
    -0.62
    IA
    -0.61
     Incarn
    -0.61
    Availability
    -0.61
    Chall
    -0.61
    CHA
    -0.61
    POSITIVE LOGITS
    aways
    0.94
     rise
    0.88
     birth
    0.80
     precedence
    0.79
     generously
    0.75
    itial
    0.75
    giving
    0.74
     Pwr
    0.72
    hift
    0.70
    awed
    0.70
    Activations Density 0.059%

    No Known Activations