© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 9343
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a change in time or situation

    oai_token-act-pair · gpt-3.5-turbo

    references to traumatic experiences and personal accounts of violence or harm

    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
     ``(
    -0.68
     \"
    -0.66
     âĢº
    -0.64
     subsid
    -0.62
    .","
    -0.62
     DRM
    -0.58
    government
    -0.58
     asteroid
    -0.58
    industrial
    -0.57
     """
    -0.57
    POSITIVE LOGITS
    Days
    0.76
    Later
    0.75
    wards
    0.74
     Months
    0.71
    emonium
    0.70
     fateful
    0.70
    advertisement
    0.70
    POST
    0.69
    odore
    0.68
    APTER
    0.68
    Activations Density 0.660%

    No Known Activations