© 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. 23689
    Prev
    Next
    INDEX
    Explanations

    informational cues, prompting the reader to seek more details

    oai_token-act-pair · gpt-3.5-turbo

    references to additional information or resources

    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
    xtap
    -0.90
    Enlarge
    -0.80
    ãĥ¼ãĥĨ
    -0.78
    ader
    -0.77
    ress
    -0.76
    Disk
    -0.76
    ãĥ¼ãĥĨãĤ£
    -0.76
    Runner
    -0.74
    atan
    -0.72
    hare
    -0.72
    POSITIVE LOGITS
     information
    0.97
     than
    0.97
     info
    0.97
     ado
    0.90
     details
    0.86
     insight
    0.84
     affordable
    0.83
     detailed
    0.82
     informative
    0.81
     advanced
    0.81
    Activations Density 0.044%

    No Known Activations