© 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. 1-RES-JB
    11. 20253
    Prev
    Next
    INDEX
    Explanations

    mentions of future possibilities or potential outcomes

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "prospect," particularly in contexts related to potential outcomes or expectations

    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
    lap
    -0.77
    lua
    -0.76
    bey
    -0.71
    ped
    -0.70
    ippy
    -0.69
    ffe
    -0.68
    perial
    -0.67
    partisan
    -0.67
    erno
    -0.65
    ork
    -0.65
    POSITIVE LOGITS
     prospect
    1.28
     prospects
    1.23
    ãĥ¼ãĥĨ
    1.04
     skelet
    0.96
     Vaugh
    0.89
     promot
    0.88
    ãĤ¼ãĤ¦ãĤ¹
    0.85
    ively
    0.85
     seeker
    0.80
    ãĥ¼ãĥĨãĤ£
    0.79
    Activations Density 0.004%

    No Known Activations