Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 20507
    Prev
    Next
    INDEX
    Explanations

    words related to salamanders and salaciousness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sal" and its variations throughout the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dominion
    -0.81
    lihood
    -0.81
    STEP
    -0.77
     Breed
    -0.71
     Breaker
    -0.69
    gaard
    -0.68
     derog
    -0.68
    urden
    -0.67
     Reboot
    -0.67
     Sets
    -0.66
    POSITIVE LOGITS
    utations
    1.16
    mone
    1.05
    istry
    1.00
    udos
    0.98
    aunch
    0.97
    utation
    0.96
    osal
    0.92
    ience
    0.90
    isbury
    0.90
    acious
    0.90
    Activations Density 0.010%

    No Known Activations