INDEX

Explanations

the word "of"

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

0:0.10

1:0.05

2:0.08

3:0.08

4:0.08

5:0.09

6:0.08

7:0.08

8:0.08

9:0.07

10:0.08

11:0.08

Negative Logits

 grav

-1.70

isms

-1.69

 occasions

-1.66

 Vehicles

-1.58

 Universe

-1.55

 trusts

-1.54

glers

-1.53

 occasion

-1.53

 Cannot

-1.51

 clutter

-1.50

POSITIVE LOGITS

gian

2.03

rious

1.84

hardt

1.75

tz

1.73

reat

1.71

laus

1.69

ín

1.69

aphael

1.69

orsi

1.69

onne

1.68

Activations Density 0.000%

the word "of"

No Comments

No Known Activations