INDEX

Explanations

phrases containing the word "turns."

oai_token-act-pair · gpt-3.5-turbo

the phrase "it turns out."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

è¦ļéĨĴ

-0.90

ordan

-0.77

atana

-0.73

aps

-0.69

fters

-0.69

ropolitan

-0.69

lain

-0.67

ainers

-0.66

capacity

-0.65

icipated

-0.64

POSITIVE LOGITS

terday

0.77

 shif

0.70

NetMessage

0.68

ĸ

0.67

 hormones

0.66

 sour

0.66

laus

0.65

 beet

0.63

 Turns

0.63

 inward

0.61

Activations Density 0.018%

phrases containing the word "turns."

the phrase "it turns out."

No Comments

No Known Activations