INDEX

Explanations

numerical values and measurements

oai_token-act-pair · gpt-3.5-turbo

numerical data related to economics and demographics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

arma

-0.67

 anonymity

-0.67

 loft

-0.64

 stash

-0.64

 parach

-0.62

utations

-0.61

 spoon

-0.59

leans

-0.58

orks

-0.58

eus

-0.58

POSITIVE LOGITS

 compared

0.86

 whereas

0.74

Footnote

0.74

 versus

0.73

.[

0.70

 apiece

0.68

".[

0.67

.(

0.67

."[

0.67

bps

0.65

Activations Density 0.242%

numerical values and measurements

numerical data related to economics and demographics

No Comments

No Known Activations