© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14899
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude or acknowledgment

    oai_token-act-pair · gpt-3.5-turbo

    expressions of gratitude

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifice
    -0.68
    igham
    -0.66
     Scand
    -0.65
    ]),
    -0.65
    romy
    -0.64
    )),
    -0.64
    igmat
    -0.63
     WATCHED
    -0.63
    angles
    -0.60
    )).
    -0.59
    POSITIVE LOGITS
     thanks
    3.92
    thanks
    2.50
     Thanks
    2.27
     thank
    2.06
     THANK
    1.91
     congratulations
    1.86
    Thanks
    1.83
     congr
    1.59
     apologies
    1.53
     courtesy
    1.52
    Activations Density 0.016%

    No Known Activations