INDEX

Explanations

words related to poisonous plants, identification tools, and online listings

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 arrang

-0.70

because

-0.69

omever

-0.67

yond

-0.65

$.

-0.65

 predec

-0.64

every

-0.62

 destro

-0.61

 respectively

-0.60

 agre

-0.59

POSITIVE LOGITS

 Profile

1.17

 âĵĺ

1.00

 Gets

0.90

 Facts

0.87

 Overview

0.85

 Â·

0.83

 Releases

0.81

 Originally

0.79

::

0.79

 welcomes

0.79

Activations Density 4.916%

words related to poisonous plants, identification tools, and online listings

No Comments

No Known Activations