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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16889
    Prev
    Next
    INDEX
    Explanations

    terms related to dialing, especially in the context of communication devices and medical procedures

    oai_token-act-pair · gpt-3.5-turbo

    references to "dial" in various contexts, often relating to adjusting or controlling something

    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
     Jed
    -0.64
     Rivals
    -0.63
    riot
    -0.60
    inventoryQuantity
    -0.59
     Werewolf
    -0.58
     Moj
    -0.57
    RI
    -0.56
     Pilgrim
    -0.56
    riks
    -0.56
     Flavoring
    -0.56
    POSITIVE LOGITS
    ysis
    1.68
    ect
    1.29
    tone
    1.00
    ogue
    0.96
    ues
    0.92
    og
    0.91
    otypes
    0.90
    dial
    0.89
    otype
    0.88
    ogs
    0.86
    Activations Density 0.046%

    No Known Activations