INDEX

Explanations

phrases related to American politics and policies

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

heed

-0.78

NB

-0.75

ijk

-0.66

orders

-0.66

*/(

-0.64

prototype

-0.63

 STATS

-0.61

operation

-0.60

_>

-0.60

isson

-0.59

POSITIVE LOGITS

ICAN

1.05

 Samoa

0.95

 Idol

0.95

 Airlines

0.91

Pie

0.84

 Express

0.79

 Legion

0.78

 Psychiatric

0.77

 McGee

0.77

èĪ

0.77

Activations Density 1.202%

phrases related to American politics and policies

No Comments

No Known Activations