INDEX

Explanations

phrases indicating directions or pathways

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_L3_Hcat_z_lr1.20e-03_l19.00e-01_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.3.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

1:0.03

2:0.08

3:0.05

4:0.02

5:0.04

6:0.04

7:0.06

8:0.04

9:0.44

10:0.08

11:0.04

Negative Logits

ufficient

-1.60

awed

-1.57

use

-1.51

pread

-1.47

Enter

-1.38

umper

-1.36

ointed

-1.33

icent

-1.33

ench

-1.32

 incor

-1.31

POSITIVE LOGITS

":[

1.31

 awhile

1.28

 Hilton

1.24

 scrimmage

1.17

 lengths

1.16

 blockers

1.16

](

1.15

hedon

1.14

fund

1.13

ramid

1.13

Activations Density 0.133%

phrases indicating directions or pathways

No Comments

No Known Activations