INDEX

Explanations

references to pricing and calorie content in food items

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.9.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

0:0.20

1:0.03

2:0.16

3:0.09

4:0.04

5:0.12

6:0.06

7:0.07

8:0.05

9:0.05

10:0.06

11:0.03

Negative Logits

tox

-2.47

 conductor

-2.41

 contag

-2.13

Hart

-2.13

 Strauss

-2.07

š

-2.07

 Infect

-2.04

 hapl

-2.02

oS

-1.98

 diagn

-1.97

POSITIVE LOGITS

 Calories

3.95

 calorie

3.75

 calories

3.73

cal

3.20

 caloric

2.87

 Calculator

2.84

 kcal

2.83

ixels

2.52

Cal

2.50

cal

2.46

Activations Density 0.004%

references to pricing and calorie content in food items

No Comments

No Known Activations