INDEX

Explanations

instances of the word "doing."

oai_token-act-pair · gpt-3.5-turbo

repetitive mentions of the word "doing"

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

lights

-0.71

liner

-0.66

Tier

-0.66

mares

-0.66

)=(

-0.65

uru

-0.64

wit

-0.63

sg

-0.62

ulates

-0.61

iewicz

-0.61

POSITIVE LOGITS

 nothing

0.80

pez

0.79

omething

0.79

oms

0.78

 brisk

0.77

omsday

0.75

ggy

0.74

å¥³

0.74

 something

0.73

ppel

0.73

Activations Density 0.048%

instances of the word "doing."

repetitive mentions of the word "doing"

No Comments

No Known Activations