© 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. 4419
    Prev
    Next
    INDEX
    Explanations

    terms related to current situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    references to current conditions and situations in various contexts

    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
    sung
    -0.74
    imb
    -0.70
    imon
    -0.66
    urat
    -0.63
    DERR
    -0.61
    gger
    -0.59
    ighters
    -0.58
    bek
    -0.58
    oser
    -0.58
    ogie
    -0.58
    POSITIVE LOGITS
     trajectory
    0.70
     parad
    0.66
     paradigm
    0.65
    ologies
    0.64
     status
    0.63
     unsustainable
    0.63
    bernatorial
    0.62
    uncture
    0.61
    APTER
    0.61
    lance
    0.61
    Activations Density 0.167%

    No Known Activations