INDEX

Explanations

words related to unethical, illegal, and criminal behavior

oai_token-act-pair · gpt-3.5-turbo

references to illegal or unethical actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ciation

-0.85

aber

-0.82

essim

-0.80

ãĥ´

-0.80

oreal

-0.79

ascript

-0.78

undrum

-0.76

ipeg

-0.73

Market

-0.73

igue

-0.73

POSITIVE LOGITS

 defendants

1.13

 mishand

1.10

 perpetrators

1.06

 whistleblowers

1.03

 contractor

1.03

 disgr

1.02

 whistleblower

1.01

 whistlebl

1.00

 contractors

1.00

 dealings

1.00

Activations Density 0.666%

words related to unethical, illegal, and criminal behavior

references to illegal or unethical actions

No Comments

No Known Activations