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. 8-RES-JB
    6. 3810
    Prev
    Next
    INDEX
    Explanations

    mentions of legal professionals or figures

    oai_token-act-pair · gpt-3.5-turbo

    mentions of attorneys or the Attorney General

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dim
    -0.70
    obyl
    -0.65
     Reincarn
    -0.64
     Dating
    -0.64
     Marathon
    -0.63
    ombat
    -0.63
    mates
    -0.62
    wn
    -0.61
     RAF
    -0.61
     Seas
    -0.60
    POSITIVE LOGITS
    general
    1.10
    General
    1.02
    iate
    0.95
     GENERAL
    0.94
    alty
    0.93
     General
    0.92
    gency
    0.92
     generals
    0.87
    alties
    0.87
     Gloria
    0.80
    Activations Density 0.039%

    No Known Activations