INDEX

Explanations

significant occurrences of the word "chair" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.08

1:0.03

2:0.07

3:0.05

4:0.03

5:0.04

6:0.20

7:0.03

8:0.06

9:0.29

10:0.03

11:0.04

Negative Logits

 Xiaomi

-3.72

 Gale

-3.69

 Gaddafi

-3.61

 Canal

-3.60

 Sail

-3.49

 Kali

-3.40

 Mozilla

-3.39

 Bungie

-3.38

 Aval

-3.29

 Mash

-3.29

POSITIVE LOGITS

 chair

7.03

 Chair

6.67

 chairs

6.56

chair

6.23

chairs

6.08

Chair

5.88

 wheelchair

5.59

 Bowen

4.22

 Schultz

4.21

itsch

3.91

Activations Density 0.002%

significant occurrences of the word "chair" in various contexts

No Comments

No Known Activations