© 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. 0-RES-JB
    11. 22214
    Prev
    Next
    INDEX
    Explanations

    acronyms related to computer technologies

    oai_token-act-pair · gpt-3.5-turbo

    specific acronyms or abbreviations related to organizations, particularly in a governmental or institutional context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lyr
    -0.72
     verse
    -0.72
     dues
    -0.71
     belie
    -0.66
     stun
    -0.64
     Bened
    -0.63
     jazz
    -0.63
     Jah
    -0.63
     tul
    -0.63
    rence
    -0.62
    POSITIVE LOGITS
    PC
    4.38
    pc
    2.29
     PC
    1.93
     pc
    1.65
    PS
    1.45
     PCs
    1.41
    PD
    1.38
    PM
    1.31
    PP
    1.31
    PG
    1.31
    Activations Density 0.013%

    No Known Activations