INDEX

Explanations

the indefinite article "an"

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

1:0.07

2:0.08

3:0.07

4:0.07

5:0.08

6:0.08

7:0.08

8:0.09

9:0.08

10:0.08

11:0.08

Negative Logits

 Thomson

-2.76

 Statistical

-2.76

 Britann

-2.68

Nun

-2.65

 sterling

-2.62

 Churchill

-2.57

 Nicola

-2.48

 Royale

-2.43

 Electoral

-2.41

 tabl

-2.39

POSITIVE LOGITS

ALT

2.48

HAL

2.46

recy

2.42

rises

2.42

 hunger

2.41

Grad

2.36

leases

2.31

uberty

2.31

 sweats

2.29

�

2.22

Activations Density 0.000%

the indefinite article "an"

No Comments

No Known Activations