© 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. 12621
    Prev
    Next
    INDEX
    Explanations

    phrases related to forcefully taking hold of something

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "grab" and its variations

    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
    xual
    -0.79
    ingen
    -0.66
    AMY
    -0.66
     Prol
    -0.65
    REDACTED
    -0.64
     Democr
    -0.63
     Explain
    -0.63
     Schwarz
    -0.63
     Discuss
    -0.62
     Archdemon
    -0.62
    POSITIVE LOGITS
    bers
    1.01
    bing
    0.98
     onto
    0.93
    bable
    0.93
    bage
    0.90
    hold
    0.84
    ber
    0.80
     hold
    0.79
     glances
    0.79
     flakes
    0.77
    Activations Density 0.041%

    No Known Activations