© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 9-RES-JB
    11. 2234
    Prev
    Next
    INDEX
    Explanations

    sections where it encourages the reader to continue reading

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    »Ĵ
    -0.85
    è¦ļéĨĴ
    -0.69
     Gleaming
    -0.68
    owl
    -0.64
    folk
    -0.61
    ription
    -0.60
    escription
    -0.59
    Downloadha
    -0.59
     Gamble
    -0.59
    ignt
    -0.58
    POSITIVE LOGITS
     Below
    0.74
     âĨĴ
    0.72
     isEnabled
    0.67
     BELOW
    0.64
    ...]
    0.64
     ARTICLE
    0.58
    below
    0.57
    hook
    0.57
    acters
    0.57
     ETH
    0.56
    Activations Density 0.025%

    No Known Activations