INDEX

Explanations

dates in the format "YYYY."

oai_token-act-pair · gpt-3.5-turbo

references to specific years, especially 2012

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

anooga

-0.84

ï¸

-0.81

phy

-0.79

itionally

-0.79

imore

-0.79

heet

-0.78

avascript

-0.77

onite

-0.74

izers

-0.74

merce

-0.73

POSITIVE LOGITS

å¹

0.87

nd

0.81

 Reincarn

0.79

 onwards

0.77

 Budget

0.67

BUS

0.67

ãģ®éŃĶ

0.66

ploy

0.66

-'

0.65

Activations Density 0.024%

dates in the format "YYYY."

references to specific years, especially 2012

No Comments

No Known Activations