INDEX

Explanations

social media interactions related to sharing or reposting

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Ret", suggesting a focus on social media interactions or shares

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

tips

-0.85

ãĥ¼ãĥĨ

-0.75

STEM

-0.74

é¾įåĸļå£«

-0.68

EngineDebug

-0.67

 hearts

-0.65

hower

-0.64

ĪĴ

-0.63

ĨĴ

-0.63

aughtered

-0.62

POSITIVE LOGITS

rieving

1.07

ribut

1.06

ention

1.06

ired

1.06

rieve

1.05

ract

0.99

ribution

0.95

reating

0.94

rieved

0.93

irement

0.93

Activations Density 0.008%

social media interactions related to sharing or reposting

instances of the word "Ret", suggesting a focus on social media interactions or shares

No Comments

No Known Activations