INDEX

Explanations

definitions or descriptions of terms

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

ersen

-0.74

igham

-0.70

 showc

-0.70

erb

-0.69

 Tiger

-0.68

 Hitman

-0.66

JM

-0.66

Args

-0.66

 Jagu

-0.64

 Hulk

-0.63

POSITIVE LOGITS

 Definition

0.91

 encompass

0.86

 defined

0.84

 combining

0.81

 encomp

0.75

 consist

0.75

defined

0.74

 "âĢ¦

0.73

 subtract

0.72

 subjective

0.71

Activations Density 0.200%

definitions or descriptions of terms

No Comments

No Known Activations