INDEX

Explanations

references to quantity or possessive constructs related to subjects or objects

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Head Attr Weights

0:0.03

1:0.03

2:0.09

3:0.06

4:0.09

5:0.04

6:0.17

7:0.22

8:0.04

9:0.06

10:0.06

11:0.06

Negative Logits

eton

-1.48

ewater

-1.47

imentary

-1.46

cade

-1.42

stown

-1.40

waukee

-1.40

emouth

-1.31

iest

-1.31

ng

-1.29

 gatherings

-1.27

POSITIVE LOGITS

olkien

1.52

 Exhibit

1.42

 Baird

1.35

ğ

1.30

awaru

1.27

 Russo

1.24

Reloaded

1.24

imi

1.24

 manga

1.23

�

1.23

Activations Density 0.000%

references to quantity or possessive constructs related to subjects or objects

No Comments

No Known Activations