INDEX

Explanations

phrases related to ceasefire violations

oai_token-act-pair · gpt-3.5-turbo

references to ceasefires and related military actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¦ļéĨĴ

-0.75

yss

-0.71

 Aires

-0.68

undy

-0.66

hler

-0.62

pes

-0.62

IRT

-0.61

 veins

-0.61

roups

-0.60

 Goose

-0.60

POSITIVE LOGITS

endment

0.95

 fulfillment

0.71

 commute

0.70

gap

0.69

 execution

0.67

escal

0.66

 deletion

0.65

zon

0.63

effect

0.62

 inconvenience

0.62

Activations Density 0.194%

phrases related to ceasefire violations

references to ceasefires and related military actions

No Comments

No Known Activations