INDEX

Explanations

phrases containing the word "Hindustan."

oai_token-act-pair · gpt-3.5-turbo

mentions of specific individuals or entities, particularly those associated with environmental topics or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ç¥ŀ

-0.77

ãĥ¯

-0.75

uador

-0.74

-0.69

ä»£

-0.66

éĹĺ

-0.65

-0.61

OHN

-0.61

00000000

-0.61

Magikarp

-0.61

POSITIVE LOGITS

 Hind

1.12

sight

0.95

enburg

0.86

cock

0.81

 todd

0.79

ley

0.78

erella

0.78

shire

0.75

 Indo

0.73

indal

0.72

Activations Density 0.007%

phrases containing the word "Hindustan."

mentions of specific individuals or entities, particularly those associated with environmental topics or organizations

No Comments

No Known Activations