© 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. 8-RES-JB
    11. 18458
    Prev
    Next
    INDEX
    Explanations

    comments on living situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "live" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sonian
    -0.80
    elight
    -0.72
    ippi
    -0.71
    reg
    -0.70
    uese
    -0.70
    enei
    -0.68
    ession
    -0.64
    ery
    -0.63
    GV
    -0.62
    essee
    -0.62
    POSITIVE LOGITS
    lihood
    1.01
     vic
    0.98
     happily
    0.93
     peacefully
    0.84
    stead
    0.83
     dangerously
    0.80
     paycheck
    0.80
     Forever
    0.79
     comfortably
    0.79
     forever
    0.74
    Activations Density 0.040%

    No Known Activations