INDEX

Explanations

reports of different types of incidents or emergencies being responded to by authorities

oai_token-act-pair · gpt-3.5-turbo

incidents related to reports of criminal activities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

DragonMagazine

-0.85

ãĤ´ãĥ³

-0.80

TED

-0.74

izons

-0.73

 evaluates

-0.73

Bonus

-0.71

wikipedia

-0.71

isSpecialOrderable

-0.70

âĨĳ

-0.69

displayText

-0.69

POSITIVE LOGITS

 disturbance

1.25

 disturbances

1.22

 gunshots

1.14

 gunfire

1.03

 intruder

0.97

 unidentified

0.95

 unexplained

0.94

 burgl

0.93

 burglary

0.91

 sightings

0.90

Activations Density 0.333%

reports of different types of incidents or emergencies being responded to by authorities

incidents related to reports of criminal activities

No Comments

No Known Activations