© 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. 19390
    Prev
    Next
    INDEX
    Explanations

    names of categories or groups

    oai_token-act-pair · gpt-3.5-turbo

    phrases that emphasize the concept of "most" or indicate the majority

    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
     Mellon
    -0.73
    vest
    -0.70
    rompt
    -0.68
    cum
    -0.64
    multipl
    -0.63
    pton
    -0.61
    instead
    -0.61
    icer
    -0.61
    abad
    -0.61
    utive
    -0.60
    POSITIVE LOGITS
     importantly
    1.37
    afa
    0.97
     notably
    0.92
    body
    0.87
    tenance
    0.84
     observers
    0.82
     Likely
    0.77
     important
    0.77
     Helpful
    0.76
     likely
    0.75
    Activations Density 0.047%

    No Known Activations