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. 10-RES-JB
    6. 18160
    Prev
    Next
    INDEX
    Explanations

    phrases related to going to places or looking for something

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate movement or direction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    soever
    -0.70
    hematically
    -0.68
    anooga
    -0.67
    quished
    -0.66
    acious
    -0.66
    imon
    -0.66
    icularly
    -0.65
    hur
    -0.64
     thri
    -0.64
    paralle
    -0.64
    POSITIVE LOGITS
     retrieve
    1.30
     investigate
    1.24
     inspect
    1.12
     meet
    1.11
     apologize
    1.05
     greet
    1.04
     find
    1.03
     visit
    1.02
     verify
    1.00
     examine
    1.00
    Activations Density 0.143%

    No Known Activations