INDEX

Explanations

phrases related to tasks or actions being performed

oai_token-act-pair · gpt-3.5-turbo

instances of the word "this" and "that" in various contexts

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

inventoryQuantity

-0.78

 Flavoring

-0.76

Dur

-0.70

Tru

-0.65

 Dwell

-0.62

 Vehicles

-0.60

osponsors

-0.59

 Surprise

-0.59

 Mile

-0.59

ãĤ¦ãĤ¹

-0.59

POSITIVE LOGITS

 entails

0.77

job

0.75

 unconsciously

0.75

 thing

0.74

 anecd

0.73

 justice

0.72

berra

0.71

 efficiently

0.70

pez

0.70

 emulate

0.69

Activations Density 0.042%

phrases related to tasks or actions being performed

instances of the word "this" and "that" in various contexts

No Comments

No Known Activations