INDEX

Explanations

phrases indicating past experiences or observations

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_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.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

0:0.07

1:0.01

2:0.07

3:0.13

4:0.02

5:0.05

6:0.09

7:0.04

8:0.02

9:0.03

10:0.35

11:0.05

Negative Logits

 inferior

-2.41

 unfit

-2.34

 deteriorating

-2.17

 precarious

-2.16

 destiny

-2.14

 doomed

-2.12

 disadvantage

-2.12

 dignity

-2.11

 accordingly

-2.10

 unworthy

-2.09

POSITIVE LOGITS

>)

2.91

 experimented

2.85

 heard

2.63

2.61

 VIDEOS

2.52

 mentioned

2.46

 noticed

2.44

 mentions

2.43

��

2.42

��

2.40

Activations Density 0.053%

phrases indicating past experiences or observations

No Comments

No Known Activations