© 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. 0-RES-JB
    11. 11466
    Prev
    Next
    INDEX
    Explanations

    adjectives or verbs related to proneness or susceptibility to certain conditions or situations

    oai_token-act-pair · gpt-3.5-turbo

    the concept of being prone to certain conditions or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gem
    -0.74
    oho
    -0.65
     Dollars
    -0.64
    atari
    -0.62
    Fif
    -0.62
     Gilmore
    -0.62
     Dot
    -0.61
     Gin
    -0.60
    izzle
    -0.60
    ENN
    -0.59
    POSITIVE LOGITS
     prone
    3.96
    prone
    2.44
     susceptible
    2.10
     plagued
    1.43
     suscept
    1.41
     riddled
    1.34
     vulnerable
    1.28
     liable
    1.28
     inclined
    1.27
     resistant
    1.27
    Activations Density 0.024%

    No Known Activations