INDEX

Explanations

mentions of the term "My"

oai_token-act-pair · gpt-3.5-turbo

the repeated mention of the word "My" related to various contexts or subjects

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

igham

-0.73

inelli

-0.72

 Uriel

-0.71

 bott

-0.70

itud

-0.69

å¥³

-0.68

eele

-0.67

 ramps

-0.67

ieri

-0.67

 forcefully

-0.66

POSITIVE LOGITS

stery

1.63

riad

1.38

anmar

1.36

stic

1.28

ths

1.27

self

1.05

opia

1.01

chal

1.00

ocard

0.99

ster

0.96

Activations Density 0.045%

mentions of the term "My"

the repeated mention of the word "My" related to various contexts or subjects

No Comments

No Known Activations