INDEX

Explanations

phrases related to controversy or disagreement

oai_token-act-pair · gpt-3.5-turbo

references to varying experiences and opinions among different groups of people

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Sphere

-0.74

 Faul

-0.73

Dug

-0.70

enegger

-0.68

issance

-0.65

 ................

-0.64

 DRAGON

-0.64

mie

-0.62

Gene

-0.60

========

-0.60

POSITIVE LOGITS

 outright

0.82

 subconscious

0.80

 unconsciously

0.73

 depending

0.72

 downright

0.72

 unwanted

0.68

 specialize

0.67

arser

0.66

 unnoticed

0.66

rants

0.66

Activations Density 0.847%

phrases related to controversy or disagreement

references to varying experiences and opinions among different groups of people

No Comments

No Known Activations