INDEX

Explanations

questions suggesting uncertainty or lack of knowledge

oai_token-act-pair · gpt-3.5-turbo

the phrase "who knows" and variations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

ciating

-0.86

herent

-0.74

ItemTracker

-0.69

aten

-0.67

Rated

-0.65

cially

-0.64

lies

-0.63

inance

-0.63

esthesia

-0.63

issance

-0.62

POSITIVE LOGITS

fri

0.64

 scen

0.63

how

0.62

ROR

0.61

rium

0.59

 Kitt

0.59

amorph

0.59

sew

0.58

 fuzz

0.58

 sunshine

0.58

Activations Density 0.047%

questions suggesting uncertainty or lack of knowledge

the phrase "who knows" and variations

No Comments

No Known Activations