INDEX

Explanations

phrases that indicate associations or connections between entities

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

0:0.02

1:0.01

2:0.06

3:0.05

4:0.12

5:0.05

6:0.06

7:0.32

8:0.04

9:0.03

10:0.08

11:0.12

Negative Logits

Response

-1.31

aylor

-1.28

reply

-1.27

arton

-1.22

xtap

-1.21

uble

-1.20

Reply

-1.20

Correct

-1.20

Sent

-1.19

stim

-1.19

POSITIVE LOGITS

 Euros

1.51

神

1.30

ership

1.30

street

1.22

 Surviv

1.21

 outlaw

1.21

 hereafter

1.20

erness

1.19

 sport

1.18

 Achievement

1.17

Activations Density 0.001%

phrases that indicate associations or connections between entities

No Comments

No Known Activations