INDEX

Explanations

instances of the word "incentive"

oai_token-act-pair · gpt-3.5-turbo Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Configuration

ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

0:0.04

1:0.03

2:0.14

3:0.04

4:0.37

5:0.07

6:0.02

7:0.02

8:0.04

9:0.11

10:0.05

11:0.02

Negative Logits

 ILCS

-1.76

USS

-1.66

isine

-1.62

RP

-1.53

isl

-1.49

CV

-1.49

////////////////////////////////

-1.49

ocity

-1.49

kernel

-1.47

affer

-1.47

POSITIVE LOGITS

 bund

1.79

 temptation

1.71

 coer

1.65

 intimidation

1.55

 encouragement

1.55

 encouraging

1.48

 tempting

1.43

 padded

1.42

 stacking

1.41

 dodge

1.41

Activations Density 0.008%

instances of the word "incentive"

No Comments

No Known Activations