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. 9-RES-JB
    6. 22343
    Prev
    Next
    INDEX
    Explanations

    text related to individuals identifying themselves in various ways, such as their political views or personal characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to self-identification and political affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hiba
    -0.75
     pretext
    -0.70
    MRI
    -0.68
     temptation
    -0.65
    ousse
    -0.63
     payoff
    -0.62
    pload
    -0.62
     surfaces
    -0.61
     surface
    -0.61
    ousand
    -0.61
    POSITIVE LOGITS
     adherent
    0.89
    odox
    0.88
     progressive
    0.85
     tolerant
    0.84
     outsider
    0.82
     fearless
    0.82
     enlightened
    0.81
     libertarian
    0.81
     conscientious
    0.79
     feminist
    0.78
    Activations Density 0.177%

    No Known Activations