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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 12726
    Prev
    Next
    INDEX
    Explanations

    phrases related to personal growth and upbringing

    oai_token-act-pair · gpt-3.5-turbo

    the word "grew" and its variations related to personal growth or development

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

    No Comments

    Negative Logits
    ioned
    -0.76
    phis
    -0.72
    oute
    -0.69
    pled
    -0.67
    dash
    -0.67
    alty
    -0.66
    zzi
    -0.65
    arrell
    -0.65
    PLIC
    -0.63
    egu
    -0.62
    POSITIVE LOGITS
     promot
    0.84
     accustomed
    0.78
    lasses
    0.75
     pains
    0.71
     exponentially
    0.69
    Growing
    0.69
    ITAL
    0.69
    lings
    0.68
    ls
    0.66
    oming
    0.66
    Activations Density 0.030%

    No Known Activations