INDEX

Explanations

phrases with the word "large" followed by a noun or adjective, particularly emphasizing the concept of quantity or size

oai_token-act-pair · gpt-3.5-turbo

references to significant quantities or sizes

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

undrum

-0.74

ISON

-0.72

mma

-0.67

ICLE

-0.66

forcer

-0.66

visor

-0.66

iom

-0.65

linger

-0.65

vantage

-0.64

POSITIVE LOGITS

 amounts

2.06

 quantities

2.02

 sums

1.66

 chunks

1.63

 doses

1.56

 volumes

1.54

 batches

1.50

 percentages

1.48

 portions

1.46

 tracts

1.44

Activations Density 0.130%

phrases with the word "large" followed by a noun or adjective, particularly emphasizing the concept of quantity or size

references to significant quantities or sizes

No Comments

No Known Activations