INDEX

Explanations

descriptions of events or activities

oai_token-act-pair · gpt-3.5-turbo 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

0:0.06

1:0.12

2:0.08

3:0.07

4:0.13

5:0.11

6:0.06

7:0.03

8:0.08

9:0.09

10:0.08

11:0.03

Negative Logits

 Psycho

-1.77

 psycho

-1.60

 Dracula

-1.59

 Illuminati

-1.58

Moz

-1.53

 Hitman

-1.51

Psy

-1.50

Psy

-1.49

 Virus

-1.49

 Euro

-1.48

POSITIVE LOGITS

CLOSE

1.91

lees

1.79

window

1.72

ilities

1.72

 COUNTY

1.72

 roadway

1.68

 sidewalks

1.67

waukee

1.63

unicip

1.62

Copyright

1.59

Activations Density 0.002%

descriptions of events or activities

No Comments

No Known Activations