INDEX

Explanations

number ranges

oai_token-act-pair · gpt-3.5-turbo

numerical ranges and quantities

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

Reviewer

-0.87

lance

-0.82

andi

-0.80

 TOUR

-0.78

liest

-0.74

iom

-0.70

Official

-0.69

MSN

-0.68

Agent

-0.66

 Prelude

-0.65

POSITIVE LOGITS

 percent

0.82

mph

0.82

 feet

0.80

 million

0.76

 minutes

0.71

 gigs

0.71

kHz

0.69

 times

0.69

rouse

0.69

 pounds

0.66

Activations Density 0.071%

number ranges

numerical ranges and quantities

No Comments

No Known Activations