INDEX

Explanations

mentions of submarines in a context that might involve military or nautical themes

oai_token-act-pair · gpt-3.5-turbo

references to submarines and related terminology

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 Marketable

-0.80

place

-0.79

giving

-0.79

grain

-0.77

heet

-0.76

eful

-0.73

tg

-0.72

reads

-0.72

kee

-0.71

 Marijuana

-0.70

POSITIVE LOGITS

 submarines

1.14

 submarine

1.12

 submar

0.99

marine

0.90

iltration

0.87

 stationed

0.82

USS

0.82

 platoon

0.80

 cables

0.79

 patrols

0.77

Activations Density 0.011%

mentions of submarines in a context that might involve military or nautical themes

references to submarines and related terminology

No Comments

No Known Activations