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. 23519
    Prev
    Next
    INDEX
    Explanations

    phrases related to conducting investigations or reviews

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to inspections and evaluations

    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
    liners
    -0.70
    usha
    -0.67
    Reason
    -0.65
     preached
    -0.64
    ulla
    -0.63
    posted
    -0.63
     tropes
    -0.62
    oldemort
    -0.62
     excuse
    -0.62
     Idea
    -0.58
    POSITIVE LOGITS
     tests
    1.41
     evaluation
    1.36
     audits
    1.34
     examination
    1.33
     inspections
    1.32
     inspection
    1.31
     investigation
    1.30
     testing
    1.30
     survey
    1.30
     feasibility
    1.29
    Activations Density 0.320%

    No Known Activations