INDEX

Explanations

phrases related to classified information/documents and handling such information

oai_token-act-pair · gpt-3.5-turbo

terms related to classified information and documents

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

annis

-0.83

odcast

-0.78

Kay

-0.77

UNCH

-0.75

oller

-0.73

 Beard

-0.71

ieft

-0.70

Philipp

-0.67

Ree

-0.66

Jackson

-0.66

POSITIVE LOGITS

 briefings

1.25

 documents

1.07

 material

0.94

 memos

0.93

 cables

0.92

 intel

0.92

 secrets

0.89

 materials

0.88

classified

0.88

 classified

0.87

Activations Density 0.067%

phrases related to classified information/documents and handling such information

terms related to classified information and documents

No Comments

No Known Activations