© 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. 7-RES-JB
    11. 23418
    Prev
    Next
    INDEX
    Explanations

    phrases related to the concept of something working or not working

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "work" and its variations in different contexts

    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
    pora
    -0.76
    ilings
    -0.73
    anamo
    -0.71
    antha
    -0.71
    gow
    -0.65
    ensor
    -0.64
    gart
    -0.64
    olic
    -0.64
    agin
    -0.64
    xual
    -0.62
    POSITIVE LOGITS
    heet
    1.09
    bench
    0.99
    hops
    0.93
     overtime
    0.90
     miracles
    0.88
     seamlessly
    0.86
     wonders
    0.84
     smoothly
    0.83
     flaw
    0.82
     differently
    0.82
    Activations Density 0.059%

    No Known Activations