INDEX

Explanations

years

oai_token-act-pair · gpt-3.5-turbo

references to specific years, particularly 2012 and 2013

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

itionally

-0.79

avascript

-0.78

phy

-0.78

ï¸

-0.77

awed

-0.77

ournals

-0.75

heet

-0.75

anooga

-0.74

itional

-0.72

onite

-0.71

POSITIVE LOGITS

å¹

0.85

nd

0.81

 onwards

0.79

 Reincarn

0.72

0.70

ãģ®éŃĶ

0.70

election

0.70

-'

0.67

assetsadobe

0.65

ploy

0.64

Activations Density 0.022%

years

references to specific years, particularly 2012 and 2013

No Comments

No Known Activations