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. 8-RES-JB
    6. 22877
    Prev
    Next
    INDEX
    Explanations

    Internet URLs

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the term "ps" or variations in different 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
    \\\\\\\\\\\\\\\\
    -0.75
     credits
    -0.71
     thirds
    -0.71
    ãĥł
    -0.68
     ObamaCare
    -0.68
     adm
    -0.68
    Bey
    -0.65
    ãĥĵ
    -0.65
    ishi
    -0.65
    ãĥĥ
    -0.64
    POSITIVE LOGITS
    ilon
    1.54
    hift
    1.06
    ystem
    1.06
    heet
    1.03
    etting
    1.02
    ylon
    1.00
    erver
    1.00
    ibilities
    0.98
    olitan
    0.97
    ervative
    0.95
    Activations Density 0.031%

    No Known Activations