© 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. 2-RES-JB
    11. 23608
    Prev
    Next
    INDEX
    Explanations

    phrases related to physically taking hold of something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "grab" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.71
    REDACTED
    -0.70
     alias
    -0.67
    bard
    -0.63
     withd
    -0.62
    repair
    -0.60
     dilig
    -0.58
     embr
    -0.58
     reconc
    -0.57
    guy
    -0.57
    POSITIVE LOGITS
     grab
    0.89
    rill
    0.88
    rolet
    0.83
    bers
    0.81
    bys
    0.80
     grabbing
    0.79
    aneers
    0.77
    ãĥ¼ãĥ³
    0.76
     onto
    0.75
    bable
    0.75
    Activations Density 0.010%

    No Known Activations