© 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. 23676
    Prev
    Next
    INDEX
    Explanations

    text that suggests a decision or recommendation based on certain criteria

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

    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
     embargo
    -0.73
     canon
    -0.72
     royalty
    -0.70
    eteen
    -0.70
     apocalypse
    -0.69
     continent
    -0.67
     slaughtered
    -0.66
     consec
    -0.65
     dose
    -0.64
     curse
    -0.64
    POSITIVE LOGITS
     Conversely
    1.21
     Such
    1.19
     Often
    1.18
     Examples
    1.17
     Additionally
    1.12
     Moreover
    1.10
     Alternatively
    1.09
     Similarly
    1.09
     Whereas
    1.07
     Likewise
    1.07
    Activations Density 0.724%

    No Known Activations