INDEX

Explanations

adjectives ending in '-y'

oai_token-act-pair · gpt-3.5-turbo

adjectives that convey emotions or conditions

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

itu

-0.71

qus

-0.71

schild

-0.71

auga

-0.69

mson

-0.68

mbuds

-0.67

aples

-0.66

arbon

-0.65

earable

-0.65

 Featured

-0.64

POSITIVE LOGITS

 juggling

0.66

 fulfillment

0.63

 awaited

0.62

ingly

0.60

jee

0.59

 dismissal

0.59

asse

0.58

haw

0.58

 delivery

0.58

 eager

0.58

Activations Density 0.210%

adjectives ending in '-y'

adjectives that convey emotions or conditions

No Comments

No Known Activations