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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 12941
    Prev
    Next
    INDEX
    Explanations

    words related to failure or unsuccessful outcomes

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "fail" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ourt
    -0.73
    iliary
    -0.69
    dar
    -0.69
    utra
    -0.68
    Austral
    -0.65
    arya
    -0.64
     Lug
    -0.63
    rete
    -0.62
    onen
    -0.62
    ript
    -0.61
    POSITIVE LOGITS
     miser
    1.24
    ingly
    0.93
     catast
    0.88
     horribly
    0.86
    lect
    0.86
     dism
    0.84
    afe
    0.81
    fail
    0.79
    hard
    0.78
    DEV
    0.72
    Activations Density 0.019%

    No Known Activations