© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 8205
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences describing combining or working together towards a common goal

    oai_token-act-pair · gpt-3.5-turbo

    infinitive verbs that indicate actions or intentions

    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
    spection
    -0.74
    Reviewer
    -0.67
    answered
    -0.66
    %%%%
    -0.65
     depends
    -0.64
    oros
    -0.63
     belongs
    -0.63
     hairs
    -0.62
     Replacement
    -0.61
    *=-
    -0.61
    POSITIVE LOGITS
     create
    1.52
     produce
    1.35
     ensure
    1.28
     develop
    1.27
     achieve
    1.26
     formulate
    1.24
     promote
    1.19
     maximize
    1.18
     deliver
    1.17
     enhance
    1.15
    Activations Density 0.147%

    No Known Activations