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. 7-RES-JB
    6. 6867
    Prev
    Next
    INDEX
    Explanations

    verbs related to failure or lack of success

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "failed" or its variations that indicate a lack of success or accomplishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atu
    -0.69
    dar
    -0.68
    onen
    -0.67
    ikh
    -0.64
    ahu
    -0.62
    inda
    -0.62
    ript
    -0.62
    enta
    -0.62
    enfranch
    -0.61
    se
    -0.60
    POSITIVE LOGITS
     miser
    1.54
     horribly
    0.94
     catast
    0.93
     dism
    0.91
    lect
    0.90
    ingly
    0.85
     muster
    0.81
    fully
    0.80
    afe
    0.78
     spectacular
    0.76
    Activations Density 0.037%

    No Known Activations