INDEX

Explanations

words related to social issues and activism such as legitimizing, tolerating, destabilizing, and revitalizing

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_fs3072-jb

Configuration

jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

3,072

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

HOU

-0.71

cloth

-0.64

 Meadows

-0.62

uden

-0.60

erity

-0.60

GAME

-0.60

words

-0.59

tower

-0.56

Ank

-0.56

Aad

-0.56

POSITIVE LOGITS

ized

2.52

ization

2.52

izing

2.48

izations

2.28

izes

2.24

izers

2.20

isation

2.17

ize

2.12

ised

2.11

izer

2.06

Activations Density 1.791%

words related to social issues and activism such as legitimizing, tolerating, destabilizing, and revitalizing

No Comments

No Known Activations