INDEX

Explanations

percentage values and numerical terms related to statistics

oai_token-act-pair · gpt-3.5-turbo

numerical data related to statistics or polling results

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

LAN

-0.75

helps

-0.68

achus

-0.68

arty

-0.67

aucus

-0.66

anamo

-0.65

gran

-0.65

Cra

-0.64

hub

-0.64

apt

-0.64

POSITIVE LOGITS

 thousand

1.08

 percent

0.99

 cents

0.94

 hundred

0.93

 pounds

0.85

een

0.84

eenth

0.80

 million

0.79

 dollars

0.77

 consecutive

0.76

Activations Density 0.038%

percentage values and numerical terms related to statistics

numerical data related to statistics or polling results

No Comments

No Known Activations