INDEX

Explanations

quantifiers and expressions of quantity

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.02

1:0.02

2:0.03

3:0.04

4:0.11

5:0.05

6:0.02

7:0.07

8:0.03

9:0.22

10:0.02

11:0.32

Negative Logits

brance

-2.65

obook

-2.46

cision

-2.40

olon

-2.19

urchase

-2.17

hip

-2.10

display

-2.09

ilage

-2.08

ón

-2.07

ongyang

-2.06

POSITIVE LOGITS

 loopholes

3.81

 avenues

3.81

 rumors

3.50

 rumours

3.47

 stories

3.44

 opportunities

3.43

 indications

3.41

 exceptions

3.41

 gaps

3.40

 reasons

3.40

Activations Density 0.173%

quantifiers and expressions of quantity

No Comments

No Known Activations