INDEX

Explanations

phrases related to being in the process of something or reviewing something

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "the."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

anie

-0.74

SPONSORED

-0.74

each

-0.71

href

-0.69

bro

-0.67

witch

-0.66

ulence

-0.66

tackle

-0.65

 accordingly

-0.64

bots

-0.62

POSITIVE LOGITS

 midst

1.44

 forefront

1.23

 vicinity

1.11

 thro

1.07

 same

1.02

 realm

1.01

 process

1.01

 middle

1.01

 fray

0.96

 trenches

0.94

Activations Density 0.147%

phrases related to being in the process of something or reviewing something

occurrences of the word "the."

No Comments

No Known Activations