INDEX

Explanations

specific acronyms, likely related to companies or organizations

oai_token-act-pair · gpt-3.5-turbo

references to a specific energy company or entity denoted by "NR"

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

 Metatron

-0.73

dates

-0.72

tumblr

-0.68

Minecraft

-0.67

 Granger

-0.64

oise

-0.63

atchewan

-0.63

 Villa

-0.63

 Cthulhu

-0.62

 undone

-0.61

POSITIVE LOGITS

NR

1.04

NR

0.87

emonic

0.87

conservancy

0.85

otiation

0.84

rint

0.84

 councill

0.77

yss

0.76

IGH

0.73

UTH

0.73

Activations Density 0.006%

specific acronyms, likely related to companies or organizations

references to a specific energy company or entity denoted by "NR"

No Comments

No Known Activations