INDEX

Explanations

interrogative phrases suggesting potential outcomes or inquiries

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_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

49,152

Data Type

float32

Hook Name

blocks.5.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

0:0.02

1:0.01

2:0.20

3:0.15

4:0.09

5:0.02

6:0.20

7:0.09

8:0.03

9:0.03

10:0.05

11:0.07

Negative Logits

ahime

-1.85

mercial

-1.45

hement

-1.41

staking

-1.37

ovies

-1.37

peror

-1.36

unctions

-1.35

uci

-1.32

visors

-1.30

iculty

-1.30

POSITIVE LOGITS

?'

1.66

?'"

1.59

?,

1.53

?!

1.51

?:

1.51

ogue

1.49

?!"

1.41

?」

1.40

 Angular

1.40

Activations Density 0.007%

interrogative phrases suggesting potential outcomes or inquiries

No Comments

No Known Activations