INDEX

Explanations

phrases related to discussion or commentary

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

0:0.01

1:0.01

2:0.11

3:0.11

4:0.11

5:0.03

6:0.04

7:0.22

8:0.04

9:0.04

10:0.14

11:0.09

Negative Logits

 disproportionately

-1.50

 nuns

-1.40

anchez

-1.33

qqa

-1.30

iscal

-1.30

 traumat

-1.30

missing

-1.28

 indicators

-1.28

 wrongly

-1.27

 underestimated

-1.26

POSITIVE LOGITS

�

1.93

 Discuss

1.72

Discuss

1.65

ipedia

1.64

 VIDEOS

1.60

 Forums

1.54

 Fame

1.49

tainment

1.49

 airs

1.47

 Prix

1.43

Activations Density 0.001%

phrases related to discussion or commentary

No Comments

No Known Activations