INDEX

Explanations

phrases or words related to positive experiences or emotions

oai_token-act-pair · gpt-3.5-turbo

the word "Good" 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 @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

âĹ¼

-0.93

ptin

-0.77

oths

-0.73

ople

-0.73

pent

-0.72

EStream

-0.70

 concoct

-0.69

RAW

-0.68

CHAT

-0.67

udic

-0.67

POSITIVE LOGITS

bye

1.20

enough

1.18

 Enough

1.03

reads

1.02

bye

0.93

 Luck

0.93

ness

0.91

sword

0.91

 Smile

0.90

 Samar

0.88

Activations Density 0.028%

phrases or words related to positive experiences or emotions

the word "Good" in various contexts

No Comments

No Known Activations