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. 22433
    Prev
    Next
    INDEX
    Explanations

    phrases indicating someone experiencing emotional or physical challenges

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "having" indicating various situations or experiences

    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
     reserv
    -0.60
    ensing
    -0.60
     Contribut
    -0.59
     Duty
    -0.58
     Teaching
    -0.57
    Reporting
    -0.57
     Posts
    -0.57
    amazon
    -0.57
    available
    -0.56
    PC
    -0.56
    POSITIVE LOGITS
     trouble
    1.17
     fun
    1.16
     dinner
    1.03
     difficulty
    1.01
     nightmares
    1.01
     lunch
    0.97
     intercourse
    0.96
     difficulties
    0.93
     supper
    0.93
     sex
    0.90
    Activations Density 0.099%

    No Known Activations