INDEX

Explanations

key terms related to investigation and scrutiny

oai_token-act-pair · gpt-3.5-turbo

phrases regarding investigation and accountability 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 @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ynthesis

-0.69

gebra

-0.68

veland

-0.67

ertility

-0.65

ellen

-0.64

culus

-0.63

gypt

-0.63

igslist

-0.62

onic

-0.62

ãĤ¼ãĤ¦ãĤ¹

-0.61

POSITIVE LOGITS

any

1.31

all

1.13

 anyone

1.08

 every

1.06

ANY

1.05

 whenever

1.03

 incidents

0.98

 offenders

0.98

ALL

0.98

 everything

0.95

Activations Density 0.566%

key terms related to investigation and scrutiny

phrases regarding investigation and accountability in various contexts

No Comments

No Known Activations