INDEX

Explanations

words relating to the United States or U.S. interactions with other countries

oai_token-act-pair · gpt-3.5-turbo

references to the United States

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 STATS

-0.69

*/(

-0.68

theless

-0.65

regor

-0.64

razil

-0.64

 Proto

-0.63

 shave

-0.62

fields

-0.62

bler

-0.62

adobe

-0.61

POSITIVE LOGITS

ADA

0.92

GI

0.87

ESSION

0.86

ierra

0.84

 Embassy

0.83

eal

0.82

.$

0.81

.,

0.80

IDA

0.80

AAF

0.79

Activations Density 0.045%

words relating to the United States or U.S. interactions with other countries

references to the United States

No Comments

No Known Activations