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. 1-RES-JB
    6. 19877
    Prev
    Next
    INDEX
    Explanations

    mentions or descriptions of shallow depths

    oai_token-act-pair · gpt-3.5-turbo

    references to shallow or superficial conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Lyn
    -0.79
    Il
    -0.74
    HCR
    -0.73
    Revolution
    -0.72
    ordan
    -0.72
    ATA
    -0.70
    upon
    -0.69
    XXXX
    -0.69
    =-=-=-=-=-=-=-=-
    -0.69
    ZI
    -0.68
    POSITIVE LOGITS
     shallow
    1.29
    emouth
    0.90
    ened
    0.80
    est
    0.78
     slope
    0.76
     submer
    0.76
     earthqu
    0.76
     wells
    0.75
     dipping
    0.75
    ening
    0.74
    Activations Density 0.005%

    No Known Activations