INDEX

Explanations

phrases related to disagreement or conflict

oai_token-act-pair · gpt-3.5-turbo

playful or whimsical language, particularly involving humorous wordplay

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Moz

-0.70

 Vega

-0.69

Jav

-0.62

 Opera

-0.61

 Balanced

-0.61

 Princ

-0.61

 Scand

-0.61

KP

-0.60

Lap

-0.60

unknown

-0.60

POSITIVE LOGITS

htaking

1.02

ards

0.93

ecause

0.89

illions

0.85

kered

0.84

hing

0.82

illion

0.82

ailable

0.81

ause

0.80

ares

0.80

Activations Density 0.075%

phrases related to disagreement or conflict

playful or whimsical language, particularly involving humorous wordplay

No Comments

No Known Activations