Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18103
    Prev
    Next
    INDEX
    Explanations

    words related to philosophical and abstract concepts, especially those related to existence and ideology

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to existential themes and crises

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    maid
    -0.84
    tower
    -0.76
    ramid
    -0.71
    ework
    -0.70
    OTA
    -0.69
    urat
    -0.68
     Cosponsors
    -0.68
    ribution
    -0.67
     ********************************
    -0.67
    rera
    -0.67
    POSITIVE LOGITS
     angst
    1.04
    ist
    0.96
     existential
    0.93
     warfare
    0.91
    ists
    0.91
     crisis
    0.89
     crises
    0.86
    etically
    0.82
     threat
    0.82
     dread
    0.81
    Activations Density 0.020%

    No Known Activations