INDEX

Explanations

words related to importance or necessity

oai_token-act-pair · gpt-3.5-turbo

terms indicating importance or necessity

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

©¶æ

-0.77

»Ĵ

-0.68

elf

-0.67

shirt

-0.66

ahs

-0.64

vom

-0.63

alks

-0.62

ËĪ

-0.62

ULTS

-0.61

oute

-0.60

POSITIVE LOGITS

to

0.92

for

0.92

 because

0.84

 enough

0.80

 towards

0.79

 determin

0.74

 factors

0.74

 toward

0.72

 insofar

0.71

 during

0.71

Activations Density 0.108%

words related to importance or necessity

terms indicating importance or necessity

No Comments

No Known Activations