INDEX

Explanations

instances where a document has been updated or corrected

oai_token-act-pair · gpt-3.5-turbo

instances of the word "updated" and related phrases indicating revisions or updates to information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aden

-0.84

zees

-0.77

hole

-0.74

holes

-0.72

ukemia

-0.72

marked

-0.72

vous

-0.71

¬¼

-0.71

pipe

-0.71

gravity

-0.71

POSITIVE LOGITS

 versions

0.85

 notifications

0.80

 accordingly

0.78

 visuals

0.77

 updates

0.76

 formulations

0.75

 updating

0.73

 hourly

0.72

 timestamp

0.71

 notification

0.70

Activations Density 0.033%

instances where a document has been updated or corrected

instances of the word "updated" and related phrases indicating revisions or updates to information

No Comments

No Known Activations