INDEX

Explanations

discussions about family structures and societal perceptions surrounding them

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_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.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

0:0.04

1:0.07

2:0.06

3:0.05

4:0.05

5:0.04

6:0.05

7:0.07

8:0.33

9:0.09

10:0.04

11:0.05

Negative Logits

umbn

-2.75

hma

-2.63

assic

-2.60

asus

-2.60

imbabwe

-2.59

anium

-2.56

iatrics

-2.48

ギ

-2.45

zsche

-2.44

TextColor

-2.44

POSITIVE LOGITS

 both

8.91

 Both

8.19

both

8.06

Both

8.02

 neither

7.59

 Neither

6.64

 either

6.43

Neither

6.25

 respectively

6.05

 Either

5.26

Activations Density 0.145%

discussions about family structures and societal perceptions surrounding them

No Comments

No Known Activations