INDEX

Explanations

capital letters indicating section headers

oai_token-act-pair · gpt-3.5-turbo

occurrences of the letter 'C' in various contexts

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

 Yamaha

-0.70

 Tinder

-0.66

 timeout

-0.65

 bottleneck

-0.62

uyomi

-0.62

 steroids

-0.61

ĸļ

-0.61

ãĥĦ

-0.61

Sov

-0.61

 Gors

-0.61

POSITIVE LOGITS

URRENT

1.25

overed

1.25

ategories

1.23

onsequ

1.20

ologne

1.18

ursed

1.16

urses

1.15

rouch

1.14

ultural

1.14

ancel

1.13

Activations Density 0.057%

capital letters indicating section headers

occurrences of the letter 'C' in various contexts

No Comments

No Known Activations