INDEX

Explanations

terms related to proper names or locations

oai_token-act-pair · gpt-3.5-turbo

proper nouns and specific names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

)."

-0.79

pic

-0.70

©¶æ¥µ

-0.65

]."

-0.64

bart

-0.64

Ic

-0.63

fu

-0.63

 Bers

-0.62

Calif

-0.62

Kab

-0.62

POSITIVE LOGITS

 consists

0.78

 refers

0.65

 specializes

0.65

 subsystem

0.63

 civilization

0.61

 comprises

0.61

 contains

0.60

 consist

0.60

 composed

0.59

 consisted

0.59

Activations Density 0.627%

terms related to proper names or locations

proper nouns and specific names

No Comments

No Known Activations