INDEX

Explanations

phrases related to expressing opinions or personal experiences

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate problem-solving or finding solutions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 broadly

-0.75

 decidedly

-0.72

umably

-0.71

 understandably

-0.67

 ostensibly

-0.65

 respectively

-0.64

 unsurprisingly

-0.64

 Notably

-0.64

surprisingly

-0.64

ensibly

-0.64

POSITIVE LOGITS

lvl

0.75

 refund

0.62

 ****

0.61

 downgrade

0.61

ļéĨĴ

0.60

cpu

0.60

 WRITE

0.59

 correction

0.59

WHY

0.59

 cure

0.59

Activations Density 1.792%

phrases related to expressing opinions or personal experiences

phrases that indicate problem-solving or finding solutions

No Comments

No Known Activations