INDEX

Explanations

phrases indicating clarification or warnings

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

1:0.00

2:0.07

3:0.15

4:0.10

5:0.02

6:0.03

7:0.33

8:0.03

9:0.04

10:0.05

11:0.10

Negative Logits

ür

-1.53

chance

-1.45

iar

-1.42

oreal

-1.41

aughtered

-1.35

ieg

-1.33

ulas

-1.31

ied

-1.28

 vain

-1.27

nell

-1.26

POSITIVE LOGITS

 Firstly

1.43

BIP

1.43

Firstly

1.42

 caveats

1.41

*:

1.40

 omission

1.35

ayson

1.32

 Clojure

1.30

 sourcing

1.29

owan

1.28

Activations Density 0.089%

phrases indicating clarification or warnings

No Comments

No Known Activations