© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 2572
    Prev
    Next
    INDEX
    Explanations

    mentions of a particular company name, "Target", especially related to customer service and operations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the brand "Target."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     traged
    -0.73
    acies
    -0.68
    ettings
    -0.66
     politic
    -0.66
    ":""},{"
    -0.62
    undy
    -0.62
     oxide
    -0.62
     tox
    -0.62
     ana
    -0.61
    ulates
    -0.61
    POSITIVE LOGITS
    icut
    0.80
    ed
    0.78
    achusetts
    0.78
     guiActiveUnfocused
    0.72
    imus
    0.71
    stadt
    0.70
    Hack
    0.69
    edin
    0.68
     Recall
    0.67
    itude
    0.67
    Activations Density 0.024%

    No Known Activations