INDEX

Explanations

instances of the word "told."

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_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

float32

Hook Name

blocks.2.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

1:0.09

2:0.08

3:0.07

4:0.08

5:0.08

6:0.08

7:0.07

8:0.08

9:0.09

10:0.07

11:0.09

Negative Logits

onto

-1.49

usc

-1.40

 sidew

-1.38

Accessory

-1.38

 slots

-1.37

UFC

-1.36

 slug

-1.34

 formations

-1.33

 corresponding

-1.29

Ich

-1.28

POSITIVE LOGITS

entious

1.82

ר

1.57

ocalyptic

1.54

iasco

1.52

soDeliveryDate

1.50

cipled

1.50

 sexism

1.49

zos

1.47

̶

1.46

 hindsight

1.43

Activations Density 0.000%

instances of the word "told."

No Comments

No Known Activations