INDEX

Explanations

specific particle and suffix combinations in words

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

1:0.03

2:0.05

3:0.05

4:0.04

5:0.04

6:0.44

7:0.03

8:0.05

9:0.06

10:0.08

11:0.05

Negative Logits

��

-1.41

 Advertisement

-1.25

 submission

-1.24

exclusive

-1.22

/-

-1.22

ollah

-1.19

••

-1.15

PRES

-1.14

 lifting

-1.14

 Tara

-1.13

POSITIVE LOGITS

emort

1.62

*/(

1.56

tarians

1.54

etooth

1.49

encia

1.49

hett

1.46

iani

1.41

hid

1.41

ciples

1.38

agall

1.34

Activations Density 0.008%

specific particle and suffix combinations in words

No Comments

No Known Activations