INDEX

Explanations

mentions of standoffs and related events involving individuals or groups

oai_token-act-pair · gpt-3.5-turbo

references to significant events involving standoffs and associated individuals

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

rates

-0.88

haps

-0.81

living

-0.75

icket

-0.75

criptions

-0.74

cribed

-0.73

idated

-0.72

rate

-0.71

lav

-0.71

ored

-0.70

POSITIVE LOGITS

 standoff

1.31

 SWAT

1.04

 Bundy

0.95

BLM

0.82

 militar

0.81

 LAPD

0.75

ishly

0.73

 Watts

0.69

inez

0.68

 SEAL

0.68

Activations Density 0.048%

mentions of standoffs and related events involving individuals or groups

references to significant events involving standoffs and associated individuals

No Comments

No Known Activations