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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-RES-JB
    6. 2184
    Prev
    Next
    INDEX
    Explanations

    the name "Sal" in various contexts

    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 @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dominion
    -0.82
    ãĥ¼ãĥĨãĤ£
    -0.81
    hower
    -0.78
     Annotations
    -0.74
    schild
    -0.73
     derog
    -0.70
     bom
    -0.69
    STEP
    -0.69
    lihood
    -0.68
     Parenthood
    -0.67
    POSITIVE LOGITS
    isbury
    1.17
    omon
    1.13
    mone
    1.04
    afi
    1.03
    adin
    1.01
    utations
    1.00
    igon
    1.00
    amon
    0.98
    utation
    0.96
    azar
    0.95
    Activations Density 0.008%

    No Known Activations