INDEX

Explanations

names of individuals along with their occupations and titles

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "and" 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 @ 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ouls

-0.79

Ĥİ

-0.79

GMT

-0.75

pees

-0.74

ETS

-0.74

éĹĺ

-0.70

OTA

-0.69

ZE

-0.68

ctions

-0.68

lot

-0.68

POSITIVE LOGITS

 therefore

1.04

 thus

1.01

 consequently

1.01

 hence

0.96

 vice

0.95

 thence

0.90

 subsequently

0.87

 then

0.86

 oversaw

0.85

 thereby

0.83

Activations Density 0.210%

names of individuals along with their occupations and titles

occurrences of the word "and" in various contexts

No Comments

No Known Activations