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

    Neuronpedia

    APICircuit 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. 1-RES-JB
    6. 24453
    Prev
    Next
    INDEX
    Explanations

    words related to weakness or frailty

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with weakness, fragility, and unsettling sensations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utics
    -0.67
    atro
    -0.67
    umat
    -0.66
    Dub
    -0.66
    errilla
    -0.65
    add
    -0.64
    adr
    -0.63
    rights
    -0.62
    gemony
    -0.62
    needs
    -0.61
    POSITIVE LOGITS
     faint
    1.25
     detectable
    0.84
     remnant
    0.83
     foul
    0.82
     faintly
    0.82
     glow
    0.80
     whiff
    0.78
    escription
    0.75
    est
    0.72
     violet
    0.72
    Activations Density 0.010%

    No Known Activations