INDEX

Explanations

proper nouns related to locations, particularly the word "Nanjing"

oai_token-act-pair · gpt-3.5-turbo

references to specific locations or entities associated with "Nan" and "Shen."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

$_

-0.82

Lago

-0.78

ib

-0.73

 Bulls

-0.73

ucci

-0.72

 disco

-0.71

hap

-0.71

Af

-0.70

PK

-0.70

 cuff

-0.69

POSITIVE LOGITS

Nan

2.12

 âĨĴ

1.77

 Shen

1.69

 Mari

1.32

 Dalton

1.21

 Stras

1.02

 Martha

0.98

 Dartmouth

0.97

Sud

0.95

Yan

0.93

Activations Density 0.041%

proper nouns related to locations, particularly the word "Nanjing"

references to specific locations or entities associated with "Nan" and "Shen."

No Comments

No Known Activations