© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6910
    Prev
    Next
    INDEX
    Explanations

    words related to fertility and prosperity, especially the term 'fertile'

    oai_token-act-pair · gpt-3.5-turbo

    descriptors of vitality and positive outcomes

    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
    ©¶æ
    -0.79
    eper
    -0.71
    BI
    -0.71
    fighter
    -0.68
    redit
    -0.68
    arent
    -0.67
    lest
    -0.67
    ition
    -0.66
    DoS
    -0.66
    trak
    -0.65
    POSITIVE LOGITS
     shores
    0.77
     Voy
    0.76
     seas
    0.76
     voyage
    0.74
     waters
    0.72
     farewell
    0.71
     sands
    0.68
    sson
    0.66
     fertile
    0.66
     adolesc
    0.65
    Activations Density 0.033%

    No Known Activations