INDEX

Explanations

references to the letter "Y"

oai_token-act-pair · gpt-3.5-turbo

the letter "Y" and its repetitions 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 @ 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

ãĥ¼ãĥĨãĤ£

-0.91

ãĥ¼ãĥĨ

-0.77

icable

-0.73

 Cortana

-0.71

entimes

-0.70

idity

-0.67

neapolis

-0.67

ilogy

-0.67

 Mehran

-0.64

 "$:/

-0.63

POSITIVE LOGITS

ield

0.97

aku

0.95

UV

0.95

ank

0.92

ORK

0.92

ahoo

0.91

ANK

0.91

LD

0.91

anks

0.90

urt

0.89

Activations Density 0.026%

references to the letter "Y"

the letter "Y" and its repetitions in various contexts

No Comments

No Known Activations