INDEX

Explanations

political discussions and references

oai_token-act-pair · gpt-3.5-turbo

references related to statements or quotes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

"!

-0.98

!",

-0.94

!".

-0.88

").

-0.84

.",

-0.83

",

-0.83

".

-0.78

"),

-0.78

".[

-0.76

"))

-0.75

POSITIVE LOGITS

 Congressman

0.88

Secretary

0.87

 GOODMAN

0.83

NPR

0.82

 Secretary

0.79

govtrack

0.73

 PRESIDENT

0.73

Senator

0.73

 Senator

0.71

glas

0.71

Activations Density 0.451%

political discussions and references

references related to statements or quotes

No Comments

No Known Activations