INDEX

Explanations

expressions of gratitude or appreciation

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "thanks to."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

ife

-0.72

anooga

-0.71

cair

-0.68

iveness

-0.68

okia

-0.68

uania

-0.67

answered

-0.66

quartered

-0.65

emo

-0.65

querque

-0.65

POSITIVE LOGITS

 tradition

0.65

 Betsy

0.65

 Luck

0.64

 sheer

0.63

 Wikipedia

0.62

 virtue

0.61

wik

0.61

 Pascal

0.60

 advancements

0.60

 Stacy

0.58

Activations Density 0.039%

expressions of gratitude or appreciation

instances of the phrase "thanks to."

No Comments

No Known Activations