INDEX

Explanations

phrases related to step-by-step instructions or processes

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

luaj

-0.80

 scraps

-0.68

coni

-0.67

United

-0.66

 Predator

-0.63

zsche

-0.62

ITED

-0.61

ãĥĩãĤ£

-0.60

 Pengu

-0.60

POSITIVE LOGITS

 steps

0.81

udic

0.76

 step

0.75

 Steps

0.75

steps

0.74

 verification

0.69

 paddle

0.68

 bypass

0.68

 stride

0.68

verning

0.68

Activations Density 0.101%

phrases related to step-by-step instructions or processes

No Comments

No Known Activations