INDEX

Explanations

the word "guide" in various contexts

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

 concess

-0.87

 spect

-0.74

 ILCS

-0.74

oubted

-0.73

ntil

-0.69

yss

-0.67

ammy

-0.66

 sovere

-0.66

asted

-0.64

 Mellon

-0.61

POSITIVE LOGITS

book

1.44

books

1.33

BOOK

1.14

posts

1.10

guide

1.07

Book

0.88

 guide

0.88

tips

0.87

kit

0.86

 guides

0.82

Activations Density 0.026%

the word "guide" in various contexts

No Comments

No Known Activations