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. 11-RES-JB
    6. 10589
    Prev
    Next
    INDEX
    Explanations

    information related to travel destinations and events happening at specific places

    oai_token-act-pair · gpt-3.5-turbo

    prepositional phrases that indicate purpose or reason

    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
     entit
    -0.74
    ouse
    -0.69
    ois
    -0.66
     thereof
    -0.65
    aretz
    -0.65
    LINE
    -0.63
    aghan
    -0.63
     BELOW
    -0.63
    Enabled
    -0.63
     persisted
    -0.63
    POSITIVE LOGITS
     consultations
    1.16
     repairs
    1.05
     questioning
    0.99
     lunch
    0.99
     dinner
    0.93
     meetings
    0.89
     briefings
    0.86
     consultation
    0.86
     inspections
    0.85
     interviews
    0.85
    Activations Density 0.105%

    No Known Activations