INDEX

Explanations

phrases related to questioning or skepticism

oai_token-act-pair · gpt-3.5-turbo

phrases that involve questioning, doubt, or skepticism towards various subjects or claims

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

udeb

-0.80

estern

-0.75

itches

-0.73

aceae

-0.72

joice

-0.72

--+

-0.71

Laughs

-0.69

brate

-0.67

Congratulations

-0.66

Introduced

-0.65

POSITIVE LOGITS

 motives

1.60

 legitimacy

1.46

 validity

1.43

 legality

1.43

 motivations

1.35

 sincerity

1.34

 viability

1.33

 adequ

1.32

 credibility

1.31

 reliability

1.31

Activations Density 0.286%

phrases related to questioning or skepticism

phrases that involve questioning, doubt, or skepticism towards various subjects or claims

No Comments

No Known Activations