INDEX

Explanations

organizations or entities with acronyms

oai_token-act-pair · gpt-3.5-turbo

acronyms and designations related to governmental organizations and agencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

*/(

-0.72

phe

-0.70

enum

-0.64

ocre

-0.61

ðĿ

-0.61

 Arcane

-0.61

Fra

-0.61

 Krish

-0.61

 Horus

-0.60

orative

-0.60

POSITIVE LOGITS

CLASSIFIED

0.88

 eaves

0.81

istani

0.78

 embassy

0.75

 homeland

0.74

uthor

0.74

istan

0.73

 footprint

0.73

 consulate

0.71

 embassies

0.70

Activations Density 0.242%

organizations or entities with acronyms

acronyms and designations related to governmental organizations and agencies

No Comments

No Known Activations