© 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. 4414
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences where the word "exactly" is used with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "not exactly."

    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
    YES
    -0.84
    çļ
    -0.80
    aman
    -0.78
     TAMADRA
    -0.75
     Enhancement
    -0.73
    bnb
    -0.72
    opoly
    -0.68
    agents
    -0.67
    iband
    -0.66
    adium
    -0.66
    POSITIVE LOGITS
     anymore
    0.85
     appe
    0.78
     bothered
    0.78
     forgiving
    0.74
     surprising
    0.74
     bother
    0.74
     flashy
    0.72
     pleasant
    0.70
     fancy
    0.70
     shy
    0.70
    Activations Density 0.054%

    No Known Activations