INDEX

Explanations

terms related to healthcare and taxation

oai_token-act-pair · gpt-3.5-turbo

terms related to healthcare and legal issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

irlf

-0.75

KEY

-0.73

 Daylight

-0.71

RAW

-0.62

pak

-0.61

APS

-0.59

earch

-0.58

merga

-0.56

Æ

-0.56

 nominate

-0.56

POSITIVE LOGITS

tenance

1.14

osterone

0.85

lihood

0.83

quartered

0.81

theless

0.80

etheless

0.80

terday

0.79

riors

0.77

acters

0.76

roying

0.71

Activations Density 0.266%

terms related to healthcare and taxation

terms related to healthcare and legal issues

No Comments

No Known Activations