INDEX

Explanations

phrases indicating clarification or emphasis

oai_token-act-pair · gpt-3.5-turbo

phrases structured around the concept of "being" or existence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

yip

-0.81

naires

-0.65

rador

-0.61

 Lines

-0.58

atis

-0.57

wi

-0.56

 Bung

-0.56

nap

-0.56

 rows

-0.56

ria

-0.55

POSITIVE LOGITS

 honest

1.12

 sure

1.11

 blunt

1.03

 able

0.99

 frank

0.93

 fair

0.85

heading

0.85

 eligible

0.82

 truthful

0.81

 careful

0.79

Activations Density 0.048%

phrases indicating clarification or emphasis

phrases structured around the concept of "being" or existence

No Comments

No Known Activations