© 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. 9-RES-JB
    11. 7481
    Prev
    Next
    INDEX
    Explanations

    the word "find" followed by different phrases

    oai_token-act-pair · gpt-3.5-turbo

    expressions of personal opinions or evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rolet
    -0.71
    luck
    -0.64
    idium
    -0.63
    istry
    -0.63
    isoft
    -0.63
     bailed
    -0.61
    oiler
    -0.59
     concess
    -0.57
     scrimmage
    -0.56
    iere
    -0.56
    POSITIVE LOGITS
     myself
    0.84
    ¿½
    0.81
    phas
    0.81
    ¤
    0.76
    ¶æ
    0.74
     it
    0.73
     yourself
    0.72
     irresistible
    0.72
     ways
    0.72
     fault
    0.72
    Activations Density 0.050%

    No Known Activations