© 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. 7252
    Prev
    Next
    INDEX
    Explanations

    contractions

    oai_token-act-pair · gpt-3.5-turbo
    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
    velop
    -0.80
    erers
    -0.70
    son
    -0.64
    sters
    -0.62
    onent
    -0.61
    cember
    -0.61
    FORE
    -0.60
    oak
    -0.60
    oint
    -0.60
    UME
    -0.60
    POSITIVE LOGITS
     gonna
    1.24
     gotta
    1.16
     been
    0.98
     got
    0.94
     gotten
    0.90
     happened
    0.87
     Been
    0.83
     going
    0.81
    been
    0.81
     Gone
    0.79
    Activations Density 0.041%

    No Known Activations