INDEX

Explanations

words related to arguments or discussions happening in events or cases

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

0:0.04

1:0.02

2:0.05

3:0.20

4:0.40

5:0.04

6:0.02

7:0.02

8:0.05

9:0.05

10:0.04

11:0.01

Negative Logits

lled

-1.43

onite

-1.41

 crate

-1.40

omet

-1.36

aph

-1.35

hill

-1.33

 hunger

-1.31

ires

-1.30

lling

-1.30

lined

-1.29

POSITIVE LOGITS

 whatsoever

2.31

soever

2.15

 imaginable

1.73

astical

1.58

else

1.47

 conceivable

1.45

 construed

1.45

 Opinion

1.45

 irrespective

1.42

perty

1.40

Activations Density 0.066%

words related to arguments or discussions happening in events or cases

No Comments

No Known Activations