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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 21428
    Prev
    Next
    INDEX
    Explanations

    words related to counterfactual conditions or hypothetical scenarios

    oai_token-act-pair · gpt-3.5-turbo

    phrases expressing disappointment or criticism related to expectations and outcomes

    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
     progresses
    -0.77
    ilial
    -0.71
     prepares
    -0.68
     accompanies
    -0.67
     interacts
    -0.66
     emphasizes
    -0.66
     enhances
    -0.65
     extends
    -0.64
     introduces
    -0.64
     informs
    -0.64
    POSITIVE LOGITS
    would
    1.04
     Would
    0.89
     would
    0.82
    =-
    0.80
    Had
    0.79
     wouldn
    0.78
    wered
    0.72
    'd
    0.68
     existed
    0.67
    anners
    0.67
    Activations Density 0.363%

    No Known Activations