INDEX

Explanations

phrases related to opening new windows or contexts

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

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.02

1:0.01

2:0.10

3:0.11

4:0.15

5:0.03

6:0.12

7:0.20

8:0.04

9:0.04

10:0.08

11:0.05

Negative Logits

 unaccount

-1.58

gging

-1.48

rolet

-1.45

esides

-1.44

vernment

-1.44

unker

-1.43

yssey

-1.41

orah

-1.41

龍

-1.40

namese

-1.40

POSITIVE LOGITS

)</

1.75

)"

1.68

 print

1.57

screen

1.40

thumbnails

1.39

papers

1.38

Initialized

1.38

Icon

1.35

Material

1.35

)."

1.33

Activations Density 0.000%

phrases related to opening new windows or contexts

No Comments

No Known Activations