INDEX

Explanations

references to food-related establishments or spaces

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

0:0.08

1:0.06

2:0.08

3:0.08

4:0.06

5:0.08

6:0.08

7:0.07

8:0.10

9:0.09

10:0.08

11:0.08

Negative Logits

 shame

-1.74

 guiActive

-1.60

 pinch

-1.52

 teaspoons

-1.52

 guilt

-1.52

Pinterest

-1.51

 Shame

-1.51

 Cups

-1.49

 PTSD

-1.47

 penny

-1.47

POSITIVE LOGITS

Corp

1.78

growth

1.69

edom

1.68

emonium

1.66

owers

1.64

ening

1.60

antle

1.56

ouses

1.56

prints

1.56

oples

1.56

Activations Density 0.000%

references to food-related establishments or spaces

No Comments

No Known Activations