INDEX

Explanations

mentions of the word "Personal."

oai_token-act-pair · gpt-3.5-turbo

references to personal topics or information

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

xual

-1.18

LER

-0.77

UMP

-0.76

GGGG

-0.74

vous

-0.73

REG

-0.72

LOS

-0.71

IVERS

-0.70

ource

-0.69

tower

-0.69

POSITIVE LOGITS

ised

1.23

ities

1.12

ized

1.10

ization

1.09

izing

1.01

 belongings

1.00

isations

0.99

isation

0.99

itÃ©

0.98

izations

0.98

Activations Density 0.039%

mentions of the word "Personal."

references to personal topics or information

No Comments

No Known Activations