INDEX

Explanations

the word "of" in the text

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

0:0.09

1:0.08

2:0.07

3:0.09

4:0.07

5:0.07

6:0.08

7:0.08

8:0.08

9:0.08

10:0.08

11:0.08

Negative Logits

chel

-3.07

rators

-2.71

umbnails

-2.68

Robin

-2.55

 scraps

-2.54

bolt

-2.53

quickShipAvailable

-2.49

arest

-2.48

 losers

-2.46

shadow

-2.45

POSITIVE LOGITS

Wid

2.95

 Wales

2.74

 Euros

2.72

 Krug

2.69

2.67

ogun

2.65

Pf

2.57

>.

2.57

 Magicka

2.57

 Publication

2.55

Activations Density 0.000%

the word "of" in the text

No Comments

No Known Activations