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. 11-RES-JB
    6. 18413
    Prev
    Next
    INDEX
    Explanations

    instances where a closer examination or inspection is mentioned in the text

    oai_token-act-pair · gpt-3.5-turbo

    terms related to inspecting or analyzing subjects

    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
    '/
    -0.69
     retaliate
    -0.69
     interchange
    -0.65
     extortion
    -0.65
    react
    -0.61
     Reincarn
    -0.60
     Decay
    -0.60
    CHAPTER
    -0.59
    AFTA
    -0.57
    iasis
    -0.56
    POSITIVE LOGITS
     reveals
    1.50
     indicates
    1.39
     showed
    1.32
     revealed
    1.31
     suggests
    1.27
     shows
    1.22
     confirms
    1.21
     indicated
    1.19
     yielded
    1.18
     uncovered
    1.17
    Activations Density 0.207%

    No Known Activations