© 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. 2307
    Prev
    Next
    INDEX
    Explanations

    important topics or issues that require attention or discussion

    oai_token-act-pair · gpt-3.5-turbo

    references to significant problems or questions that require solutions

    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
    ãĥĥãĥī
    -0.65
    renches
    -0.61
     positives
    -0.60
    ooks
    -0.60
    itters
    -0.59
    omers
    -0.57
    visors
    -0.56
    hner
    -0.56
     Levels
    -0.56
    ippers
    -0.55
    POSITIVE LOGITS
     called
    0.87
     involving
    0.81
     titled
    0.81
     resembling
    0.79
     entitled
    0.76
     consisting
    0.74
     dubbed
    0.72
     Called
    0.71
     wherein
    0.68
     named
    0.68
    Activations Density 0.542%

    No Known Activations