INDEX

Explanations

phrases that refer to superlatives and rankings

oai_token-act-pair · gpt-3.5-turbo

the repeated use of the word "the."

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

illion

-0.74

 partake

-0.72

 assume

-0.70

ambo

-0.70

dale

-0.68

OTA

-0.67

FILE

-0.66

rand

-0.65

riot

-0.64

render

-0.64

POSITIVE LOGITS

 easiest

1.14

 strongest

0.99

 safest

0.94

 hardest

0.94

 toughest

0.92

 opposite

0.91

 simplest

0.90

 same

0.90

 greatest

0.86

 largest

0.85

Activations Density 0.072%

phrases that refer to superlatives and rankings

the repeated use of the word "the."

No Comments

No Known Activations