INDEX

Explanations

terms related to hotel amenities and services

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_fs1536-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

1,536

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

 Lauder

-0.75

 Shepherd

-0.73

©¶æ¥µ

-0.73

 Koen

-0.72

 Phelps

-0.72

 Mellon

-0.70

 Keller

-0.70

Kee

-0.69

Cot

-0.69

 Elves

-0.69

POSITIVE LOGITS

usterity

1.17

withstanding

1.09

tenance

1.06

actly

1.05

terday

1.05

actory

1.02

ighty

0.99

acted

0.97

umped

0.97

mosp

0.97

Activations Density 1.667%

terms related to hotel amenities and services

No Comments

No Known Activations

terms related to hotel amenities and services

No Comments

No Known Activations