INDEX

Explanations

phrases indicating effort or difficulty

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_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

0:0.09

1:0.01

2:0.27

3:0.09

4:0.12

5:0.08

6:0.02

7:0.05

8:0.05

9:0.05

10:0.08

11:0.04

Negative Logits

uart

-1.29

eters

-1.28

olor

-1.23

lique

-1.22

multi

-1.22

represent

-1.22

ysis

-1.21

ulet

-1.18

lin

-1.14

pur

-1.12

POSITIVE LOGITS

方

1.36

 Mellon

1.35

ifiable

1.22

hetto

1.15

 luck

1.11

 speeding

1.07

ォ

1.07

 Fenrir

1.05

 darn

1.03

 Huck

1.03

Activations Density 0.082%

phrases indicating effort or difficulty

No Comments

No Known Activations