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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 12832
    Prev
    Next
    INDEX
    Explanations

    phrases related to failure

    oai_token-act-pair · gpt-3.5-turbo

    instances of failures or unsuccessful outcomes

    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
    -0.77
    iliary
    -0.73
    til
    -0.73
    selves
    -0.64
    Revolution
    -0.64
    collar
    -0.63
    Austral
    -0.62
    ourt
    -0.61
    arya
    -0.60
    dar
    -0.60
    POSITIVE LOGITS
     miser
    1.15
    fail
    0.97
     fail
    0.94
    ingly
    0.85
     failures
    0.82
     failure
    0.81
    DEV
    0.78
     horribly
    0.77
    lect
    0.77
     catast
    0.77
    Activations Density 0.014%

    No Known Activations