Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 10872
    Prev
    Next
    INDEX
    Explanations

    numbers in a time format

    oai_token-act-pair · gpt-3.5-turbo

    numeric values and time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tremend
    -0.90
     conduc
    -0.88
     carbohyd
    -0.82
     mathemat
    -0.79
     purportedly
    -0.77
     ende
    -0.75
    ournal
    -0.75
     relentlessly
    -0.75
    conservancy
    -0.74
    sonian
    -0.73
    POSITIVE LOGITS
    6666
    1.12
    %
    1.06
    3333
    0.93
     ±
    0.92
     Percentage
    0.90
    66666666
    0.89
     [+]
    0.88
     APPLIC
    0.87
     WRITE
    0.81
     Median
    0.81
    Activations Density 0.040%

    No Known Activations