© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 24075
    Prev
    Next
    INDEX
    Explanations

    references to the name "Sal" followed by either a number or specific suffixes such as -im, -ah, and -inas

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sal" in various contexts

    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
     Dominion
    -0.71
    ãĥ¼ãĥĨãĤ£
    -0.68
     dx
    -0.68
     Breaker
    -0.67
     GDDR
    -0.67
     derog
    -0.66
    hower
    -0.66
     Blueprint
    -0.64
    æ©Ł
    -0.63
     Mortal
    -0.61
    POSITIVE LOGITS
    omon
    1.03
    isbury
    0.99
    mone
    0.99
    azar
    0.98
    aska
    0.97
    utations
    0.96
    Sal
    0.94
     Sal
    0.93
    afi
    0.93
    ieri
    0.90
    Activations Density 0.006%

    No Known Activations