INDEX

Explanations

occurrences of the word "incident" and related terms, indicating discussion of events or situations

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

1:0.03

2:0.06

3:0.07

4:0.02

5:0.05

6:0.09

7:0.31

8:0.06

9:0.07

10:0.07

11:0.08

Negative Logits

 pedals

-1.22

heit

-1.18

onest

-1.11

 invests

-1.08

 trades

-1.07

 pumps

-1.06

 toes

-1.02

abase

-1.01

anty

-1.01

essor

-1.00

POSITIVE LOGITS

emort

1.30

TMZ

1.17

 Fresno

1.16

CBI

1.14

aukee

1.11

 Trooper

1.09

 abduction

1.09

angering

1.07

 Kafka

1.07

 aftermath

1.06

Activations Density 0.038%

occurrences of the word "incident" and related terms, indicating discussion of events or situations

No Comments

No Known Activations