INDEX

Explanations

phrases related to law enforcement agents

oai_token-act-pair · gpt-3.5-turbo

mentions of law enforcement or investigative agents

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

olon

-0.69

orthern

-0.64

unning

-0.64

aspberry

-0.63

numbered

-0.63

vre

-0.63

ustom

-0.62

utan

-0.61

Pew

-0.61

astery

-0.60

POSITIVE LOGITS

 agents

4.01

 agent

3.14

 Agents

3.10

agents

2.70

 Agent

2.48

agent

2.27

Agent

2.17

 operatives

1.57

 informants

1.49

 agencies

1.49

Activations Density 0.017%

phrases related to law enforcement agents

mentions of law enforcement or investigative agents

No Comments

No Known Activations