INDEX

Explanations

phrases related to technical instructions or explanations

oai_token-act-pair · gpt-3.5-turbo

references to specific physical items or entities 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 @ 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

 Chiefs

-0.60

 wildlife

-0.59

 Vacc

-0.59

 spoilers

-0.59

 Lauder

-0.58

Pri

-0.57

 Zika

-0.56

 Murdoch

-0.54

 Sail

-0.52

 Judicial

-0.52

POSITIVE LOGITS

).[

0.85

.).

0.77

%.

0.77

 itself

0.75

anooga

0.74

ļéĨĴ

0.73

+.

0.73

%).

0.72

instead

0.72

Compat

0.70

Activations Density 2.057%

phrases related to technical instructions or explanations

references to specific physical items or entities in various contexts

No Comments

No Known Activations