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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 10826
    Prev
    Next
    INDEX
    Explanations

    words related to daily routines and activities

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of significant actions or events related to home, work, or familial contexts

    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
     utilize
    -0.98
    rollment
    -0.96
     utilizes
    -0.94
     enrollment
    -0.91
     prioritize
    -0.91
    defense
    -0.89
     customizable
    -0.89
     finalized
    -0.86
    Additionally
    -0.85
     FTC
    -0.84
    POSITIVE LOGITS
    £
    1.40
     £
    1.39
     Yorkshire
    1.36
     Thatcher
    1.31
    England
    1.27
     paed
    1.23
    Britain
    1.23
    Scotland
    1.22
     apologise
    1.21
     rubbish
    1.19
    Activations Density 1.101%

    No Known Activations