© 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. 10-RES-JB
    11. 12076
    Prev
    Next
    INDEX
    Explanations

    instances of the phrase "not so"

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.62
    ertodd
    -0.60
     overflow
    -0.60
     (>
    -0.59
    MAP
    -0.58
     expire
    -0.57
    viron
    -0.56
    neum
    -0.56
     Eth
    -0.55
    DERR
    -0.54
    POSITIVE LOGITS
     much
    1.15
    much
    0.87
    bered
    0.85
    vier
    0.83
     forgiving
    0.83
     lucky
    0.83
     fortunate
    0.81
     easy
    0.79
     simple
    0.75
     subtly
    0.75
    Activations Density 0.033%

    No Known Activations