INDEX

Explanations

references to leaked information and confidential documents

oai_token-act-pair · gpt-3.5-turbo

references to leaked information or documents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

oran

-0.81

rians

-0.78

vil

-0.77

alach

-0.74

==

-0.70

igel

-0.69

============

-0.67

ellen

-0.66

phasis

-0.66

aple

-0.65

POSITIVE LOGITS

 leaked

0.92

 leaks

0.87

 confidential

0.84

Leaks

0.84

 leaking

0.79

 leak

0.77

 documents

0.74

sheets

0.74

 snippets

0.74

 closet

0.73

Activations Density 0.014%

references to leaked information and confidential documents

references to leaked information or documents

No Comments

No Known Activations