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. 4-RES-JB
    6. 23184
    Prev
    Next
    INDEX
    Explanations

    references to specific events or occasions such as music festivals or sports tournaments

    oai_token-act-pair · gpt-3.5-turbo

    references to seasonal events, particularly summer and spring

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

    No Comments

    Negative Logits
    otomy
    -0.78
    cffff
    -0.73
    pez
    -0.73
    opausal
    -0.73
     scanner
    -0.72
     pseudonym
    -0.71
    berus
    -0.70
    paio
    -0.70
    ansas
    -0.69
    ounter
    -0.69
    POSITIVE LOGITS
     Fever
    0.85
    brook
    0.84
    Course
    0.83
     Arbor
    0.81
    lings
    0.80
     Agenda
    0.79
    water
    0.78
    bridge
    0.78
    fields
    0.77
    belt
    0.76
    Activations Density 0.018%

    No Known Activations