INDEX

Explanations

gerunds or present participles

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.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

0:0.08

1:0.08

2:0.08

3:0.08

4:0.08

5:0.08

6:0.08

7:0.08

8:0.07

9:0.09

10:0.08

11:0.07

Negative Logits

fam

-2.80

 estab

-2.79

rek

-2.77

hao

-2.60

 municip

-2.58

fen

-2.52

GREEN

-2.52

wx

-2.49

 domest

-2.47

eli

-2.47

POSITIVE LOGITS

DVD

2.73

 Buffy

2.72

 DVDs

2.69

BYU

2.64

Joy

2.62

 Comed

2.58

 Cinem

2.53

 Cath

2.52

 cinem

2.49

 subtitles

2.37

Activations Density 0.000%

gerunds or present participles

No Comments

No Known Activations