INDEX

Explanations

words related to policies or actions that are focused on specific goals or outcomes

oai_token-act-pair · gpt-3.5-turbo

words related to the concept of "organizing" or "organizers."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

lap

-0.74

 gulf

-0.74

 shaved

-0.66

 mountainous

-0.65

street

-0.65

 lifeless

-0.64

 utmost

-0.62

 talented

-0.62

 disemb

-0.61

 neighboring

-0.61

POSITIVE LOGITS

iser

1.33

iatus

1.14

isers

1.07

otonin

0.96

TAIN

0.87

vier

0.81

ãĤ¼ãĤ¦ãĤ¹

0.80

edIn

0.79

 glim

0.78

 âĶľ

0.77

Activations Density 0.006%

words related to policies or actions that are focused on specific goals or outcomes

words related to the concept of "organizing" or "organizers."

No Comments

No Known Activations