INDEX

Explanations

references to political figures and global events or entities, particularly from Getty Images

oai_token-act-pair · gpt-3.5-turbo

references to Getty Images

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stood

-0.89

 vain

-0.68

 wise

-0.67

 sediment

-0.63

 reinvest

-0.61

 parasitic

-0.60

 bitters

-0.60

 favor

-0.60

 chilling

-0.59

 misunderstood

-0.59

POSITIVE LOGITS

sburg

1.88

 Images

1.33

sburgh

1.05

Images

0.91

Film

0.86

images

0.83

PLIED

0.82

æ©

0.82

Accessory

0.81

photo

0.80

Activations Density 0.009%

references to political figures and global events or entities, particularly from Getty Images

references to Getty Images

No Comments

No Known Activations