INDEX

Explanations

references to foreign entities

oai_token-act-pair · gpt-3.5-turbo

terms related to foreign entities and their interactions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

illation

-0.87

hots

-0.81

byss

-0.80

++++

-0.79

chens

-0.77

lain

-0.76

 DRAG

-0.76

aurus

-0.75

 GOODMAN

-0.75

FUL

-0.75

POSITIVE LOGITS

 affairs

1.10

 nationals

1.07

 countries

0.91

 languages

0.90

 shores

0.88

 embassies

0.85

 nations

0.84

 Affairs

0.84

 observers

0.83

 governments

0.82

Activations Density 0.020%

references to foreign entities

terms related to foreign entities and their interactions

No Comments

No Known Activations