INDEX

Explanations

phrases related to rules, regulations, and enforcement

oai_token-act-pair · gpt-3.5-turbo

content related to authority and regulations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

neath

-0.68

Registered

-0.64

 nutshell

-0.64

âĵĺ

-0.63

llers

-0.62

 Trilogy

-0.61

 Twins

-0.59

nova

-0.58

 Kinnikuman

-0.58

=""

-0.58

POSITIVE LOGITS

 deemed

1.03

 deem

0.87

 warranted

0.85

 threat

0.84

 deems

0.84

 jeopard

0.83

 threatened

0.83

 threats

0.83

 endanger

0.83

 reasonably

0.81

Activations Density 0.747%

phrases related to rules, regulations, and enforcement

content related to authority and regulations

No Comments

No Known Activations