INDEX

Explanations

phrases related to political figures and actions

oai_token-act-pair · gpt-3.5-turbo

references to political figures and their actions

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 overload

-0.73

 hybrids

-0.73

 âĸĪ

-0.68

 selves

-0.67

 grind

-0.67

 Swarm

-0.66

 Meow

-0.65

 Zombies

-0.64

 ourselves

-0.64

 metab

-0.63

POSITIVE LOGITS

enegger

0.98

assad

0.93

itone

0.89

announced

0.84

reprene

0.82

 veto

0.81

ozy

0.81

 resigned

0.81

 resign

0.79

Senate

0.79

Activations Density 1.175%

phrases related to political figures and actions

references to political figures and their actions

No Comments

No Known Activations