INDEX

Explanations

verbs and phrases indicating potential actions or capabilities

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

1:0.02

2:0.08

3:0.10

4:0.12

5:0.03

6:0.26

7:0.14

8:0.02

9:0.05

10:0.06

11:0.05

Negative Logits

 announcer

-1.35

 sovereignty

-1.33

 executions

-1.24

AMA

-1.20

 optional

-1.20

 consultations

-1.19

 Valkyrie

-1.18

 commentary

-1.18

terday

-1.17

 consultation

-1.17

POSITIVE LOGITS

gettable

1.61

ract

1.50

én

1.50

ipher

1.44

 VIEW

1.42

hett

1.37

iard

1.37

fy

1.36

anes

1.32

idable

1.30

Activations Density 0.012%

verbs and phrases indicating potential actions or capabilities

No Comments

No Known Activations