INDEX

Explanations

phrases related to upholstery or furniture design

oai_token-act-pair · gpt-3.5-turbo

terms related to the concept of "holistic."

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

EED

-0.76

 fierce

-0.67

 Fang

-0.62

Cly

-0.60

ngth

-0.59

Eag

-0.58

FUL

-0.58

XL

-0.57

hips

-0.55

 exponentially

-0.54

POSITIVE LOGITS

ocaust

1.25

idays

1.18

stery

0.97

tering

0.93

itaire

0.93

mes

0.92

phe

0.87

spection

0.86

ters

0.85

icz

0.84

Activations Density 0.025%

phrases related to upholstery or furniture design

terms related to the concept of "holistic."

No Comments

No Known Activations