INDEX

Explanations

phrases related to negative effects or consequences caused by actions or events

oai_token-act-pair · gpt-3.5-turbo

phrases or terms related to incidents and their effects

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ardless

-0.68

orest

-0.67

nesday

-0.66

 Anthropology

-0.65

Educ

-0.64

 Username

-0.64

ocene

-0.64

essor

-0.63

olate

-0.63

cknowled

-0.63

POSITIVE LOGITS

 havoc

1.24

 disturbance

1.01

 damage

0.95

 headaches

0.93

 uproar

0.90

 downfall

0.87

 miscarriage

0.87

 panic

0.86

 disruption

0.86

 stir

0.85

Activations Density 0.175%

phrases related to negative effects or consequences caused by actions or events

phrases or terms related to incidents and their effects

No Comments

No Known Activations