INDEX

Explanations

phrases indicating surprising or unexpected revelations

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate a consequential or revealing outcome

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ropolitan

-0.74

atana

-0.72

 Colleg

-0.69

è¦ļéĨĴ

-0.68

ordan

-0.66

riot

-0.65

riots

-0.65

ities

-0.64

lain

-0.63

icipated

-0.61

POSITIVE LOGITS

ĸ

0.76

Ī

0.74

WT

0.71

ĳ

0.71

terday

0.70

\\\\\\\\\\\\\\\\

0.69

¸

0.67

coat

0.66

Ĺ

0.66

 beet

0.66

Activations Density 0.023%

phrases indicating surprising or unexpected revelations

phrases that indicate a consequential or revealing outcome

No Comments

No Known Activations