INDEX

Explanations

the word "thanks" followed by a verb or noun phrase indicating positive outcomes or actions

oai_token-act-pair · gpt-3.5-turbo

instances of the word "thanks" indicating expressions of gratitude or acknowledgment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

chip

-0.72

cknowled

-0.71

eg

-0.62

qua

-0.61

ivas

-0.60

ilt

-0.59

igmat

-0.59

----------------

-0.58

 Held

-0.57

stall

-0.57

POSITIVE LOGITS

lining

0.69

 renovations

0.66

 periods

0.63

 favour

0.63

ersed

0.63

wcs

0.63

 adherence

0.62

 advancements

0.62

iments

0.62

aneously

0.61

Activations Density 0.143%

the word "thanks" followed by a verb or noun phrase indicating positive outcomes or actions

instances of the word "thanks" indicating expressions of gratitude or acknowledgment

No Comments

No Known Activations