INDEX

Explanations

instances related to wars or battles

oai_token-act-pair · gpt-3.5-turbo

references to warfare and significant battles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Lisa

-0.87

DOE

-0.82

etsy

-0.82

Node

-0.82

Plug

-0.81

perm

-0.80

ethyst

-0.80

LED

-0.78

Ell

-0.78

 Yelp

-0.77

POSITIVE LOGITS

 warfare

2.00

 combatants

1.83

 battles

1.80

 wars

1.76

 battlefield

1.72

war

1.72

 battle

1.67

 skirm

1.64

battle

1.61

 fighting

1.58

Activations Density 0.618%

instances related to wars or battles

references to warfare and significant battles

No Comments

No Known Activations