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. 6-RES-JB
    6. 22133
    Prev
    Next
    INDEX
    Explanations

    mentions of professions or fields of expertise

    oai_token-act-pair · gpt-3.5-turbo

    the conjunction "and" used frequently in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GMT
    -0.78
    :(
    -0.74
    ONSORED
    -0.73
    xt
    -0.72
    igmatic
    -0.69
    Character
    -0.67
    ishi
    -0.65
    ukong
    -0.64
    nt
    -0.63
    Ĥİ
    -0.62
    POSITIVE LOGITS
     assorted
    0.95
    doms
    0.91
     retirees
    0.81
     alike
    0.78
     pundits
    0.77
     other
    0.75
     personalities
    0.75
     others
    0.74
     bureaucrats
    0.74
    vous
    0.74
    Activations Density 0.210%

    No Known Activations