INDEX

Explanations

the use of the word "to" in various contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.12

1:0.02

2:0.12

3:0.02

4:0.04

5:0.10

6:0.06

7:0.07

8:0.14

9:0.09

10:0.03

11:0.13

Negative Logits

pox

-1.67

athi

-1.65

apan

-1.61

ghazi

-1.60

assian

-1.57

>[

-1.55

cens

-1.54

coded

-1.52

english

-1.50

amental

-1.47

POSITIVE LOGITS

 locate

1.69

 rall

1.67

 mobilize

1.51

 utilize

1.51

 minimize

1.50

 erect

1.46

 locating

1.45

 rescue

1.45

 repair

1.44

 conserve

1.42

Activations Density 0.039%

the use of the word "to" in various contexts

No Comments

No Known Activations