INDEX

Explanations

words related to towers

oai_token-act-pair · gpt-3.5-turbo

references to towers

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

ãĤ±

-0.81

dit

-0.79

 Lives

-0.78

âĸ¬âĸ¬

-0.72

rities

-0.69

furt

-0.69

 Taste

-0.69

 Vacc

-0.68

é»Ĵ

-0.67

fecture

-0.66

POSITIVE LOGITS

 towers

1.22

 tower

1.17

tower

1.05

 Towers

0.95

 heights

0.93

 erected

0.92

 crane

0.89

 skysc

0.86

 blocks

0.79

 taller

0.75

Activations Density 0.013%

words related to towers

references to towers

No Comments

No Known Activations