INDEX

Explanations

phrases related to military ranks and actions

oai_token-act-pair · gpt-3.5-turbo

references to military rank or titles

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

arers

-0.57

Prev

-0.53

âĸ¬

-0.53

+.

-0.51

isible

-0.50

*.

-0.50

sylv

-0.49

iqueness

-0.49

Ħ¢

-0.49

 exists

-0.49

POSITIVE LOGITS

 stint

0.70

 career

0.63

DUI

0.61

 wheelchair

0.61

 guitar

0.56

 rehab

0.54

 himself

0.54

 paternity

0.54

 solo

0.53

 hospital

0.53

Activations Density 1.150%

phrases related to military ranks and actions

references to military rank or titles

No Comments

No Known Activations