INDEX

Explanations

references to terrorist attacks and military operations

oai_token-act-pair · gpt-3.5-turbo

references to attacks or violence related to geopolitical events

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

uid

-0.91

drawn

-0.91

galitarian

-0.85

 wrinkles

-0.83

roo

-0.81

ãĤ´ãĥ³

-0.80

ripp

-0.77

igmat

-0.75

itus

-0.75

lied

-0.75

POSITIVE LOGITS

 civilians

1.28

 unarmed

1.10

 civilian

1.07

 innocent

1.04

 embassies

1.04

 strongh

0.97

 convoy

0.96

 Kabul

0.96

 targets

0.95

 Gaza

0.92

Activations Density 0.216%

references to terrorist attacks and military operations

references to attacks or violence related to geopolitical events

No Comments

No Known Activations