INDEX

Explanations

phrases indicating a significant amount of time or effort being spent on various activities

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize significant amounts of time or effort spent on activities

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

idden

-0.77

DragonMagazine

-0.75

ipper

-0.75

ode

-0.74

atures

-0.73

cription

-0.73

raid

-0.73

²¾

-0.71

ses

-0.70

ippers

-0.69

POSITIVE LOGITS

 amounts

0.77

 meaningful

0.75

 enrichment

0.74

 convincing

0.74

 interest

0.72

 clout

0.71

 persu

0.71

 mileage

0.69

 publicity

0.68

 interesting

0.68

Activations Density 0.160%

phrases indicating a significant amount of time or effort being spent on various activities

phrases that emphasize significant amounts of time or effort spent on activities

No Comments

No Known Activations