© 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. 7-RES-JB
    11. 23999
    Prev
    Next
    INDEX
    Explanations

    words related to decision-making or consideration of options

    oai_token-act-pair · gpt-3.5-turbo

    terms related to evaluating or comparing options

    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
    esan
    -0.70
    ahime
    -0.69
    zynski
    -0.68
    etheless
    -0.67
    marriage
    -0.67
     Osc
    -0.66
    employment
    -0.66
    interrupted
    -0.66
    ilk
    -0.66
    lear
    -0.64
    POSITIVE LOGITS
     weigh
    1.04
     weights
    0.91
     weighing
    0.90
    ighed
    0.88
     heaviest
    0.76
     burdens
    0.76
    enance
    0.74
     weighed
    0.73
     scales
    0.72
    iless
    0.71
    Activations Density 0.033%

    No Known Activations