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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 2-RES-JB
    6. 16512
    Prev
    Next
    INDEX
    Explanations

    phrases related to failures or accusations of failure

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "failing."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enfranch
    -0.74
    oller
    -0.73
    ization
    -0.73
    istics
    -0.69
    ized
    -0.68
    anto
    -0.67
    idal
    -0.66
    oret
    -0.65
    utra
    -0.65
    inda
    -0.63
    POSITIVE LOGITS
     miser
    1.22
     failures
    0.86
     fail
    0.77
     failure
    0.77
     failing
    0.76
    fail
    0.75
     horribly
    0.72
     dism
    0.71
    luster
    0.70
     Failed
    0.68
    Activations Density 0.009%

    No Known Activations