INDEX

Explanations

keywords related to news headlines, such as "Replay" and "Videos"

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Replay" in relation to videos

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

kers

-0.71

 sucker

-0.71

represented

-0.70

ult

-0.70

ker

-0.69

pora

-0.65

antle

-0.65

 Mens

-0.65

EStreamFrame

-0.64

ide

-0.64

POSITIVE LOGITS

 WATCHED

0.98

 Replay

0.89

natureconservancy

0.73

 Lessons

0.71

icators

0.71

 WATCH

0.70

querque

0.69

ï

0.69

 Thumbnails

0.69

ique

0.68

Activations Density 0.012%

keywords related to news headlines, such as "Replay" and "Videos"

instances of the word "Replay" in relation to videos

No Comments

No Known Activations