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. 0-RES-JB
    6. 10634
    Prev
    Next
    INDEX
    Explanations

    phrases related to efforts that did not achieve the desired outcome

    oai_token-act-pair · gpt-3.5-turbo

    the term "unsuccessful" and its variations in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hi
    -0.66
     vibe
    -0.64
    ®
    -0.62
    pour
    -0.61
     Preview
    -0.60
     breat
    -0.60
     Enjoy
    -0.59
    Sense
    -0.59
     curves
    -0.58
     Spread
    -0.57
    POSITIVE LOGITS
     unsuccessful
    3.55
     unsuccessfully
    2.65
     futile
    1.70
     ineffective
    1.67
    successful
    1.55
    failed
    1.38
     thwarted
    1.35
     vain
    1.34
     successful
    1.33
     failed
    1.32
    Activations Density 0.020%

    No Known Activations