© 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. 12844
    Prev
    Next
    INDEX
    Explanations

    words related to actively following or seeking something

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "pursue" and its variants

    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
    immer
    -0.63
    finger
    -0.61
    uffer
    -0.60
    cious
    -0.59
    carry
    -0.58
     saline
    -0.58
    obyl
    -0.58
     crawl
    -0.58
    electric
    -0.56
    othing
    -0.56
    POSITIVE LOGITS
     pursued
    1.22
     pursue
    1.13
     pursuing
    1.01
     fixme
    0.86
    iage
    0.85
    iveness
    0.82
     avenues
    0.79
    alus
    0.78
    TAIN
    0.77
    folios
    0.77
    Activations Density 0.012%

    No Known Activations