INDEX

Explanations

words related to diplomatic or political contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the end-of-text token

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

 destro

-0.79

ä»£

-0.73

antage

-0.68

enegger

-0.65

 toget

-0.65

farious

-0.63

milo

-0.62

 disg

-0.62

jri

-0.62

akespe

-0.60

POSITIVE LOGITS

 Rates

0.81

 Finder

0.78

 Profile

0.73

 Album

0.72

 Abilities

0.70

 Transfer

0.70

 Locations

0.70

 Directory

0.69

 Reviews

0.69

 Components

0.68

Activations Density 0.420%

words related to diplomatic or political contexts

occurrences of the end-of-text token

No Comments

No Known Activations