INDEX

Explanations

phrases related to sudden intense events or actions

oai_token-act-pair · gpt-3.5-turbo

descriptions of traumatic or violent events

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.85

ãĤ´ãĥ³

-0.81

 Achieve

-0.72

 Inher

-0.71

 annually

-0.70

 Patreon

-0.69

yrights

-0.69

 endeavors

-0.68

 Architects

-0.68

ortium

-0.67

POSITIVE LOGITS

 screaming

1.02

 ..."

1.02

 panicked

1.00

 yelling

0.99

 âĢ¦"

0.97

0.95

['

0.93

 luckily

0.93

,'"

0.90

 kinda

0.90

Activations Density 0.451%

phrases related to sudden intense events or actions

descriptions of traumatic or violent events

No Comments

No Known Activations