INDEX

Explanations

phrases related to weapons and military activities

oai_token-act-pair · gpt-3.5-turbo

references to weapons and weaponry

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gres

-0.83

noon

-0.80

 coli

-0.75

forth

-0.74

lus

-0.74

 Strawberry

-0.72

mond

-0.70

âĸ¬

-0.70

 Niet

-0.68

apest

-0.68

POSITIVE LOGITS

powder

1.00

 weapons

0.89

 arsenal

0.86

 caches

0.85

 smugglers

0.83

 wielded

0.83

mith

0.82

 weapon

0.81

kit

0.81

 salute

0.81

Activations Density 0.032%

phrases related to weapons and military activities

references to weapons and weaponry

No Comments

No Known Activations