INDEX

Explanations

phrases related to exemptions or being exempted from something

oai_token-act-pair · gpt-3.5-turbo

terms related to exemptions in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ãĥ¥

-0.70

Kind

-0.70

 Roses

-0.67

 Hurricanes

-0.66

 Stro

-0.66

 Roose

-0.65

FUL

-0.63

Joy

-0.61

 Bras

-0.61

Ì¶

-0.61

POSITIVE LOGITS

 exempt

1.32

 exempted

1.18

exempt

1.18

icut

1.03

untarily

1.03

 exemptions

0.95

ively

0.87

emption

0.86

iencies

0.85

 minded

0.84

Activations Density 0.011%

phrases related to exemptions or being exempted from something

terms related to exemptions in various contexts

No Comments

No Known Activations