INDEX

Explanations

phrases related to Edward Snowden

oai_token-act-pair · gpt-3.5-turbo

mentions of Edward Snowden

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 combined

-0.68

Num

-0.67

Mid

-0.65

 pots

-0.63

 carb

-0.62

 autos

-0.62

 prem

-0.61

 combo

-0.61

kn

-0.61

 Races

-0.61

POSITIVE LOGITS

 Snowden

3.85

Snow

2.03

 Greenwald

1.92

 Assange

1.88

NSA

1.77

NSA

1.75

 WikiLeaks

1.50

 whistleblower

1.47

 Wikileaks

1.47

 Clapper

1.41

Activations Density 0.017%

phrases related to Edward Snowden

mentions of Edward Snowden

No Comments

No Known Activations