INDEX

Explanations

phrases that include the word "bits"

oai_token-act-pair · gpt-3.5-turbo

terms related to digital information or data

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

 hospital

-0.75

 sanction

-0.66

 wound

-0.65

 cause

-0.64

 reign

-0.64

 pest

-0.63

 domestic

-0.63

sed

-0.63

 title

-0.62

 Missouri

-0.61

POSITIVE LOGITS

bits

4.25

 Bits

1.42

BIT

1.23

pins

1.03

bytes

1.01

bit

1.00

istors

0.97

Bytes

0.95

 bits

0.93

uggets

0.91

Activations Density 0.025%

phrases that include the word "bits"

terms related to digital information or data

No Comments

No Known Activations