INDEX

Explanations

words related to inappropriate or offensive language

oai_token-act-pair · gpt-3.5-turbo

words related to professional or profane topics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

warm

-0.86

forth

-0.77

MENTS

-0.77

wolves

-0.72

nuts

-0.71

rers

-0.69

LESS

-0.68

MENT

-0.68

 lodge

-0.67

 Warriors

-0.67

POSITIVE LOGITS

iled

1.15

iles

1.15

iler

1.14

ilers

1.07

essor

1.06

aned

1.05

anity

1.02

iling

0.98

usion

0.98

 prof

0.93

Activations Density 0.014%

words related to inappropriate or offensive language

words related to professional or profane topics

No Comments

No Known Activations