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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RES-JB
    6. 16134
    Prev
    Next
    INDEX
    Explanations

    numerical data related to quantities or statistics

    oai_token-act-pair · gpt-3.5-turbo

    numerical data and statistics related to population trends

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    agnetic
    -0.73
    romy
    -0.69
    ovie
    -0.67
     ENG
    -0.67
    æ©
    -0.64
     purse
    -0.63
    Interstitial
    -0.61
    mbuds
    -0.60
     MAD
    -0.59
    Ħ¢
    -0.58
    POSITIVE LOGITS
     dwind
    1.00
     rises
    1.00
     tripled
    0.98
     climbed
    0.97
     climbs
    0.96
    incre
    0.94
     fluct
    0.92
     jumps
    0.92
     doubled
    0.92
     skyrocket
    0.92
    Activations Density 0.192%

    No Known Activations