INDEX

Explanations

words related to being exempt or exceptions to rules or regulations

oai_token-act-pair · gpt-3.5-turbo

terms related to legal exemptions and exclusions

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

ãĥ¥

-0.72

 Xiang

-0.67

 Roses

-0.66

aces

-0.65

plays

-0.65

 Stro

-0.64

 Gest

-0.62

 Roose

-0.62

kr

-0.61

KR

-0.61

POSITIVE LOGITS

 exempt

1.19

exempt

1.10

 exemptions

1.08

 exempted

1.05

 exemption

1.00

Reviewer

0.90

 immunity

0.89

emption

0.86

untarily

0.84

icut

0.81

Activations Density 0.020%

words related to being exempt or exceptions to rules or regulations

terms related to legal exemptions and exclusions

No Comments

No Known Activations