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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 9982
    Prev
    Next
    INDEX
    Explanations

    phrases related to global events, agreements, and political activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to significant global or political issues

    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
    itars
    -0.83
    lees
    -0.82
    hops
    -0.81
     Bits
    -0.80
    nces
    -0.80
    urches
    -0.79
     acron
    -0.79
    redients
    -0.78
     Rooms
    -0.76
    aunts
    -0.75
    POSITIVE LOGITS
     foothold
    1.01
     standpoint
    0.96
     basis
    0.93
     solution
    0.89
     showdown
    0.89
     agenda
    0.88
     presidency
    0.86
     caliphate
    0.86
     perspective
    0.86
     mindset
    0.85
    Activations Density 0.489%

    No Known Activations