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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 15527
    Prev
    Next
    INDEX
    Explanations

    words related to feelings of transcendence and magnificence

    oai_token-act-pair · gpt-3.5-turbo

    concepts related to transcendence and timelessness

    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
     Slate
    -0.67
    gered
    -0.66
     ske
    -0.64
     solicitation
    -0.63
     allele
    -0.62
    Alias
    -0.62
    sol
    -0.62
     Garrison
    -0.61
     subtitle
    -0.60
     stray
    -0.60
    POSITIVE LOGITS
     transcend
    1.08
    cend
    0.99
    ental
    0.84
    ancy
    0.81
    cffffcc
    0.79
    ulously
    0.79
    math
    0.76
    ence
    0.74
    mable
    0.73
    frey
    0.73
    Activations Density 0.021%

    No Known Activations