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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9-RES-JB
    6. 16990
    Prev
    Next
    INDEX
    Explanations

    phrases related to difficult situations or challenges

    oai_token-act-pair · gpt-3.5-turbo

    references to various societal issues or challenges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Correction
    -0.71
    ():
    -0.64
    share
    -0.61
    olis
    -0.59
    ipel
    -0.58
     Hemisphere
    -0.58
     Narc
    -0.57
    ename
    -0.57
    âĦ¢:
    -0.55
     Strauss
    -0.55
    POSITIVE LOGITS
    these
    1.05
     all
    1.04
    etc
    0.98
    among
    0.98
     among
    0.98
    all
    0.97
    none
    0.95
     etc
    0.94
    These
    0.91
    anything
    0.89
    Activations Density 1.107%

    No Known Activations