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. 10-RES-JB
    6. 1849
    Prev
    Next
    INDEX
    Explanations

    terms related to unions and local organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to local entities and instances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EStreamFrame
    -0.68
    dayName
    -0.65
    emouth
    -0.57
     purs
    -0.55
    astern
    -0.52
    omi
    -0.51
    liction
    -0.51
    ework
    -0.51
    ersive
    -0.51
     behavi
    -0.50
    POSITIVE LOGITS
     225
    1.50
     226
    1.48
     149
    1.48
     324
    1.46
     205
    1.45
     129
    1.45
     224
    1.45
     230
    1.45
     330
    1.45
     3000
    1.45
    Activations Density 0.530%

    No Known Activations