© 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. 2-RES-JB
    11. 17711
    Prev
    Next
    INDEX
    Explanations

    the word "verge" with a high level of activation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the phrase "on the verge," indicating impending change or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    war
    -0.75
    add
    -0.74
    imposed
    -0.73
    mut
    -0.71
    tan
    -0.71
    zie
    -0.67
    inn
    -0.67
    unc
    -0.65
    har
    -0.65
     performed
    -0.64
    POSITIVE LOGITS
     verge
    1.02
    veyard
    0.77
    ï¸
    0.76
    uary
    0.73
    uates
    0.68
    ÃĽ
    0.68
    lihood
    0.68
     Wem
    0.68
    terness
    0.65
    ologies
    0.65
    Activations Density 0.007%

    No Known Activations