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. 6-RES-JB
    6. 10605
    Prev
    Next
    INDEX
    Explanations

    places or locations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to camping and outdoor activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disg
    -0.72
     gren
    -0.66
     resent
    -0.64
    dyl
    -0.62
     aven
    -0.59
     crest
    -0.59
    ritten
    -0.59
     brig
    -0.59
    etsk
    -0.59
     destro
    -0.59
    POSITIVE LOGITS
     Relationship
    1.06
     Away
    0.94
     Definition
    0.93
     Guys
    0.92
     Month
    0.92
     Own
    0.92
     Programs
    0.92
     Experience
    0.91
     Disorder
    0.91
     Reviews
    0.91
    Activations Density 0.602%

    No Known Activations