INDEX

Explanations

references to vigilance or watching for something

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.attn.hook_z

Hook Layer

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.11

3:0.06

4:0.17

5:0.02

6:0.03

7:0.36

8:0.03

9:0.04

10:0.05

11:0.06

Negative Logits

YouTube

-1.47

Engineers

-1.47

 sham

-1.46

CTV

-1.46

rane

-1.33

isec

-1.32

NBC

-1.31

SourceFile

-1.28

init

-1.27

 wink

-1.26

POSITIVE LOGITS

abilia

1.67

auder

1.67

efer

1.66

 goodies

1.58

 barg

1.58

 elusive

1.53

 furnish

1.53

aband

1.51

 lett

1.45

 affordability

1.45

Activations Density 0.001%

references to vigilance or watching for something

No Comments

No Known Activations