INDEX

Explanations

the word "who" and variations of it, indicating a focus on identifying individuals or experts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res_post_32k-oai

Configuration

jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

32,768

Data Type

torch.float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

Dataset

Skylion007/openwebtext

Activation Function

topk

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SPONSORED

-0.69

INA

-0.64

 expiration

-0.63

Spread

-0.62

 laughter

-0.62

 mockery

-0.61

 ANGEL

-0.61

 Mechdragon

-0.60

Myth

-0.60

 Clock

-0.60

POSITIVE LOGITS

 oversaw

1.05

 oversees

1.05

 supervised

0.96

 heads

0.93

 directs

0.91

 helped

0.87

 worked

0.86

 chaired

0.85

 represents

0.85

 superv

0.85

Activations Density 0.546%

the word "who" and variations of it, indicating a focus on identifying individuals or experts

No Comments

No Known Activations