INDEX

Explanations

words related to defense or protection against potential harm or danger

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_fs768-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_768

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

768

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

etry

-0.85

toc

-0.73

ittal

-0.73

ffe

-0.71

estial

-0.70

prints

-0.70

astery

-0.69

 largeDownload

-0.67

miah

-0.66

orld

-0.66

POSITIVE LOGITS

 adversity

1.42

 pesky

1.15

 temptation

1.14

 pests

1.08

 boredom

1.06

 criticism

1.05

 challenges

1.03

 harassment

1.02

 threats

1.01

 obstacles

1.00

Activations Density 5.328%

words related to defense or protection against potential harm or danger

No Comments

No Known Activations