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. 4965
    Prev
    Next
    INDEX
    Explanations

    the word "Sal" specifically

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual named Sal

    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
    ãĥ¼ãĥĨãĤ£
    -0.81
     Dominion
    -0.77
    hower
    -0.77
     Annotations
    -0.71
     derog
    -0.71
    lihood
    -0.71
     clipboard
    -0.71
     bom
    -0.69
    STEP
    -0.69
    schild
    -0.69
    POSITIVE LOGITS
    isbury
    1.19
    omon
    1.12
    mone
    1.09
    utations
    1.06
    adin
    1.06
    igon
    1.03
    afi
    1.02
    amon
    1.01
    utation
    0.99
    ient
    0.98
    Activations Density 0.009%

    No Known Activations