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. 2-RES-JB
    6. 20568
    Prev
    Next
    INDEX
    Explanations

    medical terms related to the adrenal gland and the city of Reno, Nevada

    oai_token-act-pair · gpt-3.5-turbo

    terms related to adrenaline and its effects, as well as references to Reno, Nevada

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onica
    -0.86
    士
    -0.77
    soever
    -0.75
     Roz
    -0.74
    llan
    -0.72
     Settlement
    -0.72
    esley
    -0.71
     Laurent
    -0.70
    gie
    -0.70
    square
    -0.70
    POSITIVE LOGITS
     adrenaline
    1.21
    aline
    0.99
     adren
    0.99
     exhilar
    0.97
     thrill
    0.94
    ulic
    0.90
     anticipation
    0.79
     reflex
    0.78
    ibal
    0.76
     excitement
    0.76
    Activations Density 0.030%

    No Known Activations