INDEX

Explanations

references to systemic issues or disparities affecting communities

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

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.3.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.04

2:0.08

3:0.07

4:0.03

5:0.04

6:0.12

7:0.14

8:0.09

9:0.16

10:0.07

11:0.09

Negative Logits

ologne

-1.13

autions

-1.11

 Scholars

-1.08

 Cout

-1.02

YP

-1.01

oubt

-1.00

roit

-0.98

issors

-0.98

vantage

-0.97

ACL

-0.97

POSITIVE LOGITS

cffffcc

1.30

 WATCHED

1.20

idon

1.03

oslav

1.02

 Tycoon

0.99

cery

0.98

tac

0.97

STDOUT

0.95

etooth

0.95

idia

0.94

Activations Density 0.035%

references to systemic issues or disparities affecting communities

No Comments

No Known Activations