INDEX

Explanations

phrases that express a comparison or equivalence

oai_token-act-pair · gpt-3.5-turbo

phrases indicating statements or assertions about conditions or situations

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

actively

-0.64

 harass

-0.62

urring

-0.62

bies

-0.61

 exists

-0.59

 personalities

-0.58

 moderators

-0.58

 conquer

-0.58

luaj

-0.58

existent

-0.58

POSITIVE LOGITS

Correct

0.71

PORT

0.69

EMS

0.68

quickShipAvailable

0.67

ECA

0.66

 unsur

0.64

acca

0.64

 Shea

0.63

unny

0.62

 Scythe

0.61

Activations Density 0.149%

phrases that express a comparison or equivalence

phrases indicating statements or assertions about conditions or situations

No Comments

No Known Activations