INDEX

Explanations

phrases related to alignment or agreement

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "in line" with various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

CVE

-1.00

ilt

-0.78

soever

-0.77

DAC

-0.69

è¦ļéĨĴ

-0.68

 Seym

-0.67

rely

-0.67

 BaseType

-0.65

icably

-0.65

ble

-0.63

POSITIVE LOGITS

backer

0.86

breakers

0.73

arity

0.72

meal

0.72

eyes

0.72

stad

0.69

dated

0.69

suit

0.66

stri

0.66

naires

0.65

Activations Density 0.019%

phrases related to alignment or agreement

instances of the phrase "in line" with various contexts

No Comments

No Known Activations