INDEX

Explanations

words related to rigidity or stiffness

oai_token-act-pair · gpt-3.5-turbo

terms related to rigidity and stiffness

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

ulhu

-0.88

obyl

-0.73

hex

-0.71

 Occupations

-0.69

uyomi

-0.67

 Ancients

-0.66

 Hiroshima

-0.64

ctica

-0.64

 Partnership

-0.64

 Shutterstock

-0.63

POSITIVE LOGITS

ening

1.12

eners

1.12

est

1.06

nesses

1.04

ened

1.03

ener

1.02

er

1.00

eling

0.98

eness

0.89

 stiff

0.86

Activations Density 0.015%

words related to rigidity or stiffness

terms related to rigidity and stiffness

No Comments

No Known Activations