INDEX

Explanations

words related to legal issues and global politics

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

ĨĴ

-1.03

ħĭ

-0.86

essee

-0.85

¬¼

-0.81

éĹĺ

-0.80

sylv

-0.72

insula

-0.72

ĸļ

-0.70

CRIP

-0.69

stakes

-0.69

POSITIVE LOGITS

riage

1.19

thur

1.10

rier

1.07

acter

1.06

rington

1.03

ried

1.01

rival

0.98

beit

0.98

lington

0.97

allel

0.96

Activations Density 2.074%

words related to legal issues and global politics

No Comments

No Known Activations