INDEX

Explanations

unexpected or important revelations or twists in a story

oai_token-act-pair · gpt-3.5-turbo

terms and phrases that indicate surprising or significant events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

endars

-0.73

 Decay

-0.66

emale

-0.66

azeera

-0.65

 cabinets

-0.65

abella

-0.64

 Administ

-0.64

 originals

-0.64

hner

-0.63

 Dise

-0.63

POSITIVE LOGITS

1.10

:'

1.00

:,

0.97

:-

0.95

:(

0.95

 whereby

0.94

!:

0.92

:[

0.92

 involving

0.92

:#

0.92

Activations Density 0.367%

unexpected or important revelations or twists in a story

terms and phrases that indicate surprising or significant events

No Comments

No Known Activations