INDEX

Explanations

items or concepts related to shopping or product features

oai_token-act-pair · gpt-3.5-turbo

words that indicate comparisons or similarities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

hovah

-0.76

enary

-0.73

arbon

-0.72

 Inquiry

-0.69

rontal

-0.64

ITNESS

-0.63

ÙĴ

-0.62

ribution

-0.61

orse

-0.61

idate

-0.61

POSITIVE LOGITS

 namely

0.88

including

0.80

such

0.72

 including

0.71

 ours

0.64

viz

0.64

Berry

0.64

ATK

0.61

etsk

0.58

 include

0.58

Activations Density 0.189%

items or concepts related to shopping or product features

words that indicate comparisons or similarities

No Comments

No Known Activations