© 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. 12978
    Prev
    Next
    INDEX
    Explanations

    references to potential or possibility

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "prospects" related to potential opportunities or situations

    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
    ffe
    -0.76
    lap
    -0.74
    lua
    -0.68
    fried
    -0.68
    dry
    -0.68
    gar
    -0.67
    lez
    -0.65
    gur
    -0.64
    ped
    -0.64
    waters
    -0.64
    POSITIVE LOGITS
     prospects
    1.08
     prospect
    0.98
    ively
    0.95
     skelet
    0.93
    icons
    0.91
    uring
    0.85
    urities
    0.81
     Prospect
    0.80
    osition
    0.77
    ures
    0.77
    Activations Density 0.007%

    No Known Activations