INDEX

Explanations

phrases related to legal and official procedures

oai_token-act-pair · gpt-3.5-turbo

actions taken in response to allegations or complaints

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 dared

-0.75

gling

-0.72

Imagine

-0.71

eat

-0.70

 famously

-0.67

 versus

-0.66

literally

-0.66

Too

-0.66

ankind

-0.65

billion

-0.64

POSITIVE LOGITS

 inquiries

1.11

 enqu

1.10

 consultations

1.06

 contingency

1.03

 refunds

0.99

 clarification

0.98

 feedback

0.92

 consultation

0.92

 updates

0.92

 counselling

0.91

Activations Density 0.553%

phrases related to legal and official procedures

actions taken in response to allegations or complaints

No Comments

No Known Activations