INDEX

Explanations

the indefinite article "a"

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

0:0.07

1:0.08

2:0.08

3:0.07

4:0.08

5:0.07

6:0.08

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

BLIC

-2.93

cia

-2.75

 Confeder

-2.74

 Spain

-2.69

 Ethiopia

-2.65

 Saban

-2.58

 Shogun

-2.56

 Spani

-2.48

 Maria

-2.46

 Crimean

-2.45

POSITIVE LOGITS

 tails

2.71

 claw

2.61

aunts

2.55

 pairs

2.48

fits

2.44

utory

2.40

 Finder

2.38

 dots

2.35

 claws

2.34

oggles

2.27

Activations Density 0.000%

the indefinite article "a"

No Comments

No Known Activations