INDEX

Explanations

verbs indicating action or change in a specific context

oai_token-act-pair · gpt-3.5-turbo

verbs associated with actions and concepts in social, political, and economic contexts

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

ĺħ

-0.69

 Hurricanes

-0.64

utenberg

-0.62

 Dolphins

-0.61

IZE

-0.61

allery

-0.61

 foremost

-0.59

 constitu

-0.59

 Legislative

-0.59

 Directorate

-0.58

POSITIVE LOGITS

ings

1.56

able

1.47

ables

1.43

ability

1.21

ers

1.20

ational

1.08

aways

1.07

away

1.05

backs

1.05

ement

1.02

Activations Density 0.516%

verbs indicating action or change in a specific context

verbs associated with actions and concepts in social, political, and economic contexts

No Comments

No Known Activations