INDEX

Explanations

phrases related to subscription offers and newsletters

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

2:0.06

3:0.11

4:0.08

5:0.03

6:0.07

7:0.32

8:0.04

9:0.06

10:0.08

11:0.07

Negative Logits

aukee

-1.80

olesc

-1.78

neapolis

-1.76

andals

-1.66

rifice

-1.61

essen

-1.58

 disadvant

-1.55

onne

-1.49

cule

-1.49

antry

-1.48

POSITIVE LOGITS

 periodic

1.68

 Newsletter

1.59

 Subscribe

1.50

Subscribe

1.46

 Audio

1.44

 Sound

1.43

 Torrent

1.41

 Signal

1.36

 Transcript

1.34

 subscribing

1.33

Activations Density 0.002%

phrases related to subscription offers and newsletters

No Comments

No Known Activations