INDEX

Explanations

references to surveillance or monitoring technologies

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

1:0.02

2:0.07

3:0.30

4:0.02

5:0.02

6:0.10

7:0.14

8:0.04

9:0.08

10:0.07

11:0.08

Negative Logits

querque

-1.33

agascar

-1.29

enegger

-1.28

ional

-1.15

ailability

-1.13

itely

-1.12

sembly

-1.10

ortunately

-1.09

ablo

-1.08

 newcom

-1.08

POSITIVE LOGITS

cious

1.24

agall

1.11

 Blanc

1.08

Frameworks

1.07

eteenth

1.06

 downs

1.03

Avg

1.02

 stalls

1.02

tex

1.01

 sidelines

0.99

Activations Density 0.002%

references to surveillance or monitoring technologies

No Comments

No Known Activations