INDEX

Explanations

mentions related to political figures and events, especially concerning public appearances and relationships

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

significant political events or statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 12-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.11.hook_resid_post

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

 Defin

-0.82

 Libraries

-0.78

{:

-0.73

 civilisation

-0.69

 Delete

-0.69

 Mandatory

-0.69

 Âł Âł Âł Âł Âł Âł Âł Âł

-0.67

 âĸĪ

-0.67

 Shotgun

-0.67

 Penal

-0.66

POSITIVE LOGITS

 aides

1.19

 amid

1.03

 politically

1.01

ablishment

0.99

 onstage

0.97

 ideologically

0.95

 partisan

0.94

 domestically

0.94

 POLITICO

0.94

 surrog

0.93

Activations Density 0.557%

mentions related to political figures and events, especially concerning public appearances and relationships

significant political events or statements

No Comments

No Known Activations