INDEX

Explanations

terms related to protection and defense

oai_token-act-pair · gpt-3.5-turbo

concepts related to protection and shielding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

onde

-0.75

 Kinn

-0.69

subject

-0.63

NC

-0.62

————————

-0.62

itled

-0.61

 Fever

-0.60

 Vide

-0.60

 Asylum

-0.60

zos

-0.60

POSITIVE LOGITS

 against

0.99

against

0.85

iveness

0.82

 protects

0.82

ously

0.81

ively

0.78

 protecting

0.77

 perimeter

0.76

 guarding

0.76

 shielding

0.76

Activations Density 0.138%

terms related to protection and defense

concepts related to protection and shielding

No Comments

No Known Activations