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. 20176
    Prev
    Next
    INDEX
    Explanations

    phrases related to events or actions being carried out or completed

    oai_token-act-pair · gpt-3.5-turbo

    variations of the verb "be" in different contexts

    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
    robat
    -0.57
    Camp
    -0.55
     Brach
    -0.54
    Um
    -0.54
    Fr
    -0.54
    stroke
    -0.52
    luster
    -0.51
    Exc
    -0.50
     Amid
    -0.50
    Tips
    -0.50
    POSITIVE LOGITS
     implemented
    1.14
     ported
    1.13
     rewritten
    1.10
     released
    1.09
     published
    1.08
     merged
    1.07
     updated
    1.07
     reprinted
    1.06
     uploaded
    1.04
     deleted
    1.04
    Activations Density 0.274%

    No Known Activations