INDEX

Explanations

phrases enclosed in quotation marks

oai_token-act-pair · gpt-3.5-turbo

phrases denoting quotes or citations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

thur

-0.72

ife

-0.69

²¾

-0.65

forth

-0.64

ason

-0.64

worldly

-0.61

Picture

-0.60

mber

-0.60

imates

-0.59

ãĥ¼ãĥĨãĤ£

-0.58

POSITIVE LOGITS

/"

0.96

0.74

 referring

0.72

 meaning

0.68

([

0.67

advertisement

0.66

SPONSORED

0.65

ymes

0.65

 labeling

0.63

>>\

0.62

Activations Density 0.108%

phrases enclosed in quotation marks

phrases denoting quotes or citations

No Comments

No Known Activations