INDEX

Explanations

references to political figures and entities

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

0:0.03

1:0.11

2:0.15

3:0.06

4:0.04

5:0.08

6:0.06

7:0.10

8:0.15

9:0.03

10:0.07

11:0.05

Negative Logits

¶

-1.12

panic

-1.09

��

-1.05

="#

-1.00

naires

-0.97

"}],"

-0.97

coins

-0.95

ikers

-0.95

blers

-0.94

pee

-0.93

POSITIVE LOGITS

ONSORED

1.18

 Edited

1.14

 millenn

1.12

 Printed

1.10

 Retrieved

1.02

 reprint

1.01

 reprinted

1.01

 OFFIC

0.98

 Topics

0.97

 archived

0.95

Activations Density 0.337%

references to political figures and entities

No Comments

No Known Activations