INDEX

Explanations

technical terms related to software testing

oai_token-act-pair · gpt-3.5-turbo

references to testing activities and processes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

theless

-0.83

taboola

-0.80

ACP

-0.72

soType

-0.69

leans

-0.67

 traged

-0.67

cci

-0.67

NetMessage

-0.67

vernment

-0.66

CHO

-0.66

POSITIVE LOGITS

imony

1.08

udo

0.99

osterone

0.99

 suite

0.93

rador

0.85

 dummy

0.82

 suites

0.81

imon

0.76

 testers

0.75

orer

0.71

Activations Density 0.047%

technical terms related to software testing

references to testing activities and processes

No Comments

No Known Activations