INDEX

Explanations

phrases related to holding law enforcement accountable and discussing their actions beyond what is necessary

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names of individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 conver

-0.69

pport

-0.68

 upside

-0.67

 overwhelming

-0.66

antic

-0.65

planes

-0.65

 stereotypes

-0.65

 overhe

-0.64

 taxing

-0.64

tro

-0.61

POSITIVE LOGITS

Jr

1.53

Sr

1.25

PhD

1.08

MD

1.02

Jr

1.02

aka

0.93

Es

0.92

JR

0.86

MPH

0.84

JD

0.82

Activations Density 0.169%

phrases related to holding law enforcement accountable and discussing their actions beyond what is necessary

proper nouns, specifically names of individuals

No Comments

No Known Activations