INDEX

Explanations

terms related to government surveillance and intelligence agencies

oai_token-act-pair · gpt-3.5-turbo

references to governmental surveillance and intelligence programs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

 Wrest

-0.84

ciation

-0.79

 Dise

-0.77

 Converted

-0.76

rition

-0.75

 Kinn

-0.75

Unity

-0.75

 Wheels

-0.74

 relegation

-0.74

 Sadd

-0.73

POSITIVE LOGITS

NSA

1.88

 surveillance

1.85

 spying

1.84

NSA

1.79

 Surveillance

1.73

 FISA

1.67

 eaves

1.65

 wiret

1.64

illance

1.63

Privacy

1.52

Activations Density 0.840%

terms related to government surveillance and intelligence agencies

references to governmental surveillance and intelligence programs

No Comments

No Known Activations