INDEX

Explanations

references to defending and protecting

oai_token-act-pair · gpt-3.5-turbo

terms related to defense or protection

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

 Crowley

-0.76

 Elijah

-0.75

aldi

-0.74

LIN

-0.74

luence

-0.72

 Clover

-0.71

 Cinnamon

-0.71

oter

-0.70

reprene

-0.70

acci

-0.69

POSITIVE LOGITS

 defense

1.93

 defenses

1.85

defense

1.75

 defending

1.74

 defences

1.74

 defend

1.71

 defence

1.69

 defensive

1.68

 protection

1.65

 Defense

1.63

Activations Density 0.334%

references to defending and protecting

terms related to defense or protection

No Comments

No Known Activations