INDEX

Explanations

recent updates or news information

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Updated" indicating updates or changes in information

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ankind

-0.76

rarily

-0.73

velt

-0.73

plin

-0.71

gravity

-0.71

aden

-0.70

pload

-0.70

ohm

-0.70

ppings

-0.70

ardless

-0.69

POSITIVE LOGITS

 timestamp

0.70

 VERS

0.68

irement

0.66

 Explan

0.66

 versions

0.65

 Coverage

0.65

 Date

0.63

 version

0.62

 alert

0.62

 Alert

0.61

Activations Density 0.021%

recent updates or news information

instances of the word "Updated" indicating updates or changes in information

No Comments

No Known Activations