INDEX

Explanations

phrases related to actions and events

oai_token-act-pair · gpt-3.5-turbo

phrases related to significant events and their implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Flavoring

-0.86

thood

-0.68

Ħ¢

-0.66

inas

-0.63

?).

-0.62

 Practices

-0.62

onga

-0.60

 cass

-0.59

ahs

-0.58

 invests

-0.58

POSITIVE LOGITS

 Arpaio

0.77

uay

0.74

 Kafka

0.68

 divided

0.62

 perplex

0.61

 Danielle

0.60

 Berger

0.60

 Hollande

0.60

 Netanyahu

0.59

 Rath

0.59

Activations Density 1.110%

phrases related to actions and events

phrases related to significant events and their implications

No Comments

No Known Activations