INDEX

Explanations

proper nouns, particularly the name "Nate."

oai_token-act-pair · gpt-3.5-turbo

the name "Nate" in various contexts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

externalActionCode

-0.79

hips

-0.75

;;;;;;;;;;;;

-0.74

,,,,

-0.73

omething

-0.68

Catalog

-0.67

;;

-0.66

inventoryQuantity

-0.66

ODUCT

-0.65

POSITIVE LOGITS

 Nate

1.16

 Silver

0.84

elson

0.81

elsen

0.81

caster

0.78

nels

0.76

 Diaz

0.74

laus

0.73

 Schmidt

0.73

 Oliver

0.72

Activations Density 0.005%

proper nouns, particularly the name "Nate."

the name "Nate" in various contexts

No Comments

No Known Activations