INDEX

Explanations

phrases related to changes or shifts in focus or direction

oai_token-act-pair · gpt-3.5-turbo

phrases indicating shifts or changes in direction or focus

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

wordpress

-0.75

enery

-0.71

bath

-0.70

wic

-0.68

COMPLE

-0.68

listed

-0.65

IFE

-0.63

 Brune

-0.63

imentary

-0.62

brance

-0.61

POSITIVE LOGITS

 favoring

0.84

raviolet

0.82

focus

0.80

 reliance

0.76

 focus

0.75

 toward

0.75

essim

0.73

 extremes

0.70

 specialization

0.70

 direction

0.70

Activations Density 0.204%

phrases related to changes or shifts in focus or direction

phrases indicating shifts or changes in direction or focus

No Comments

No Known Activations