INDEX

Explanations

terms related to defense and security

oai_token-act-pair · gpt-3.5-turbo

terms related to defense and security

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

ellen

-0.83

 Tanz

-0.73

cker

-0.72

outh

-0.72

ient

-0.72

 Bland

-0.71

Doe

-0.67

Jenn

-0.64

Honest

-0.63

Hop

-0.62

POSITIVE LOGITS

 defence

1.10

 defences

1.02

 Defence

0.98

 defense

0.82

 defends

0.78

tackle

0.77

folios

0.77

 ministry

0.75

 Defense

0.73

 solicitor

0.73

Activations Density 0.011%

terms related to defense and security

terms related to defense and security

No Comments

No Known Activations