INDEX

Explanations

organizations, institutions, and government-related entities

oai_token-act-pair · gpt-3.5-turbo

references to government and political entities

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

ITNESS

-0.71

zsche

-0.66

eatures

-0.64

lopp

-0.58

undai

-0.57

 Canaver

-0.57

features

-0.56

hillary

-0.54

å°Ĩ

-0.54

oenix

-0.54

POSITIVE LOGITS

 lest

0.88

 alone

0.87

 unless

0.86

 because

0.83

 indefinitely

0.82

 coffers

0.80

 amid

0.79

($

0.79

 despite

0.79

 (Â£

0.78

Activations Density 0.568%

organizations, institutions, and government-related entities

references to government and political entities

No Comments

No Known Activations