INDEX

Explanations

mentions of specific names, likely related to a person or a company

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names or terms related to strokes or healthcare

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

UAL

-0.81

ãĤº

-0.79

 appropriation

-0.75

 Odyssey

-0.73

 Pathfinder

-0.70

*/(

-0.70

 Prometheus

-0.68

imilation

-0.67

 conscious

-0.65

pole

-0.62

POSITIVE LOGITS

 Stro

1.12

pping

0.91

ller

0.89

zen

0.88

zes

0.86

kes

0.80

ppings

0.80

pper

0.80

cade

0.79

ppers

0.78

Activations Density 0.016%

mentions of specific names, likely related to a person or a company

mentions of specific names or terms related to strokes or healthcare

No Comments

No Known Activations