INDEX

Explanations

words related to coding, software development, and technical terminology

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res_fs24576-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 experiments

-0.67

 scraps

-0.65

 implementations

-0.64

 dismantling

-0.64

 calculations

-0.64

 Blueprint

-0.62

 archives

-0.61

 nightmares

-0.60

 collaborations

-0.60

 optimizations

-0.59

POSITIVE LOGITS

Äĵ

0.91

-.

0.90

É

0.88

âĢİ

0.85

xual

0.82

 signifies

0.80

/,

0.80

qq

0.78

Åį

0.78

-,

0.78

Activations Density 0.225%

words related to coding, software development, and technical terminology

No Comments

No Known Activations