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. 4336
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names of places

    oai_token-act-pair · gpt-3.5-turbo

    references to actions and events in narrative contexts

    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
    orld
    -0.85
     emergencies
    -0.84
    terday
    -0.74
     Gon
    -0.71
     apocalypse
    -0.71
     mars
    -0.70
    ylum
    -0.69
    eday
    -0.66
     enthusi
    -0.65
    Job
    -0.65
    POSITIVE LOGITS
    dfx
    0.86
     Cosponsors
    0.82
    ãĥĩãĤ£
    0.79
     Rubber
    0.78
    px
    0.76
    rued
    0.76
    ilic
    0.73
    Ã
    0.71
    uscript
    0.70
    ãĥ¼ãĥ
    0.69
    Activations Density 0.251%

    No Known Activations